{"seed": 763, "task": "acde_medium", "difficulty": "medium", "step": 1, "state": {"patient_condition": "serious", "remaining_time_minutes": 17.0, "failed_hospitals": [], "visited_hospitals": [], "ambulance_status": "en_route"}, "action": {"hospital_id": "H3", "policy_score": 0.3576442928451815, "strategy": "safe policy + anti-stupidity guard"}, "outcome": {"status": "PARTIAL", "reason": "Initial triage completed; transfer monitoring still required"}, "reward": 0.39} {"seed": 763, "task": "acde_medium", "difficulty": "medium", "step": 2, "state": {"patient_condition": "stable", "remaining_time_minutes": 17.0, "failed_hospitals": [], "visited_hospitals": ["H3"], "ambulance_status": "in_transit"}, "action": {"hospital_id": "H2", "policy_score": 0.29701578480684365, "strategy": "balanced policy + guided-exploration"}, "outcome": {"status": "REJECTED", "reason": "Condition became irreversible after delays"}, "reward": -0.54} {"seed": 763, "task": "acde_medium", "difficulty": "medium", "step": 3, "state": {"patient_condition": "stable", "remaining_time_minutes": 17.0, "failed_hospitals": ["H2"], "visited_hospitals": ["H3", "H2"], "ambulance_status": "rerouting"}, "action": {"hospital_id": "H3", "policy_score": 0.4146231513578693, "strategy": "risk-aware policy + anti-stupidity guard"}, "outcome": {"status": "ACCEPTED", "reason": "Patient stabilized after delayed admission"}, "reward": 0.89} {"seed": 202601, "task": "acde_medium", "difficulty": "medium", "step": 1, "state": {"patient_condition": "critical", "remaining_time_minutes": 15.0, "failed_hospitals": [], "visited_hospitals": [], "ambulance_status": "en_route"}, "action": {"hospital_id": "H1", "policy_score": 0.32220992776375695, "strategy": "safe policy + critical triage"}, "outcome": {"status": "PARTIAL", "reason": "Admitted with delays: prolonged transfer strain"}, "reward": 0.30000000000000004} {"seed": 202601, "task": "acde_medium", "difficulty": "medium", "step": 2, "state": {"patient_condition": "unstable", "remaining_time_minutes": 15.0, "failed_hospitals": [], "visited_hospitals": ["H1"], "ambulance_status": "in_transit"}, "action": {"hospital_id": "H2", "policy_score": 0.21774606157953277, "strategy": "balanced policy + critical triage"}, "outcome": {"status": "PARTIAL", "reason": "Condition worsened but remains temporarily transferable"}, "reward": 0.24999999999999997} {"seed": 202601, "task": "acde_medium", "difficulty": "medium", "step": 3, "state": {"patient_condition": "unstable", "remaining_time_minutes": 15.0, "failed_hospitals": [], "visited_hospitals": ["H1", "H2"], "ambulance_status": "in_transit"}, "action": {"hospital_id": "H1", "policy_score": 0.3998021612932113, "strategy": "balanced policy + critical triage + anti-stupidity guard"}, "outcome": {"status": "REJECTED", "reason": "Condition became irreversible after delays"}, "reward": -0.65} {"seed": 202601, "task": "acde_medium", "difficulty": "medium", "step": 4, "state": {"patient_condition": "unstable", "remaining_time_minutes": 15.0, "failed_hospitals": ["H4"], "visited_hospitals": ["H1", "H2", "H4"], "ambulance_status": "rerouting"}, "action": {"hospital_id": "H3", "policy_score": 0.33161740733197975, "strategy": "risk-aware policy"}, "outcome": {"status": "ACCEPTED", "reason": "Patient stabilized after delayed admission"}, "reward": 0.86} {"seed": 202701, "task": "acde_medium", "difficulty": "medium", "step": 1, "state": {"patient_condition": "critical", "remaining_time_minutes": 14.0, "failed_hospitals": [], "visited_hospitals": [], "ambulance_status": "en_route"}, "action": {"hospital_id": "H2", "policy_score": 0.4993941041253803, "strategy": "safe policy"}, "outcome": {"status": "PARTIAL", "reason": "Initial triage completed; transfer monitoring still required"}, "reward": 0.15} {"seed": 202701, "task": "acde_medium", "difficulty": "medium", "step": 2, "state": {"patient_condition": "critical", "remaining_time_minutes": 14.0, "failed_hospitals": [], "visited_hospitals": ["H2"], "ambulance_status": "in_transit"}, "action": {"hospital_id": "H2", "policy_score": 0.4995113329525376, "strategy": "balanced policy + critical triage + guided-exploration + anti-stupidity guard"}, "outcome": {"status": "REJECTED", "reason": "Hospital cannot admit: No specialist available"}, "reward": -0.7300000000000001} {"seed": 202701, "task": "acde_medium", "difficulty": "medium", "step": 3, "state": {"patient_condition": "critical", "remaining_time_minutes": 14.0, "failed_hospitals": ["H2"], "visited_hospitals": ["H2"], "ambulance_status": "rerouting"}, "action": {"hospital_id": "H1", "policy_score": 0.13235217826749926, "strategy": "risk-aware policy + anti-stupidity guard"}, "outcome": {"status": "REJECTED", "reason": "Critical treatment machine failed at admission"}, "reward": -0.68} {"seed": 202701, "task": "acde_medium", "difficulty": "medium", "step": 4, "state": {"patient_condition": "critical", "remaining_time_minutes": 14.0, "failed_hospitals": ["H2", "H1"], "visited_hospitals": ["H2", "H1"], "ambulance_status": "rerouting"}, "action": {"hospital_id": "H4", "policy_score": 0.029253047748109114, "strategy": "risk-aware policy"}, "outcome": {"status": "ACCEPTED", "reason": "Emergency stabilization at last attempt"}, "reward": 0.64} {"seed": 202801, "task": "acde_medium", "difficulty": "medium", "step": 1, "state": {"patient_condition": "critical", "remaining_time_minutes": 15.0, "failed_hospitals": [], "visited_hospitals": [], "ambulance_status": "en_route"}, "action": {"hospital_id": "H5", "policy_score": 0.3751805639973787, "strategy": "safe policy + critical triage + anti-stupidity guard"}, "outcome": {"status": "ACCEPTED", "reason": "Patient admitted and treatment began"}, "reward": 1.0} {"seed": 555, "task": "acde_hard", "difficulty": "hard", "step": 1, "state": {"patient_condition": "critical", "remaining_time_minutes": 11.0, "failed_hospitals": [], "visited_hospitals": [], "ambulance_status": "en_route"}, "action": {"hospital_id": "H1", "policy_score": 0.38407571202711865, "strategy": "safe policy + critical triage"}, "outcome": {"status": "PARTIAL", "reason": "Admitted with delays: prolonged transfer strain, patient worsened during transfer"}, "reward": 0.225} {"seed": 555, "task": "acde_hard", "difficulty": "hard", "step": 2, "state": {"patient_condition": "unstable", "remaining_time_minutes": 11.0, "failed_hospitals": [], "visited_hospitals": ["H1"], "ambulance_status": "in_transit"}, "action": {"hospital_id": "H4", "policy_score": 0.30280335749574794, "strategy": "balanced policy + critical triage + anti-stupidity guard"}, "outcome": {"status": "REJECTED", "reason": "Hospital cannot admit: ICU unavailable"}, "reward": -0.5800000000000001} {"seed": 555, "task": "acde_hard", "difficulty": "hard", "step": 3, "state": {"patient_condition": "unstable", "remaining_time_minutes": 11.0, "failed_hospitals": ["H4"], "visited_hospitals": ["H1", "H4"], "ambulance_status": "rerouting"}, "action": {"hospital_id": "H1", "policy_score": 0.3878258255871748, "strategy": "risk-aware policy + anti-stupidity guard"}, "outcome": {"status": "REJECTED", "reason": "Hospital cannot admit: ICU unavailable, No specialist available"}, "reward": -0.75} {"seed": 555, "task": "acde_hard", "difficulty": "hard", "step": 4, "state": {"patient_condition": "critical", "remaining_time_minutes": 11.0, "failed_hospitals": ["H4", "H1"], "visited_hospitals": ["H1", "H4"], "ambulance_status": "rerouting"}, "action": {"hospital_id": "H2", "policy_score": 0.12805651759694409, "strategy": "risk-aware policy"}, "outcome": {"status": "REJECTED", "reason": "Condition became irreversible after delays"}, "reward": -0.6} {"seed": 655, "task": "acde_hard", "difficulty": "hard", "step": 1, "state": {"patient_condition": "critical", "remaining_time_minutes": 11.0, "failed_hospitals": [], "visited_hospitals": [], "ambulance_status": "en_route"}, "action": {"hospital_id": "H5", "policy_score": 0.3700866134698383, "strategy": "safe policy + critical triage"}, "outcome": {"status": "REJECTED", "reason": "Hospital cannot admit: Hospital overloaded"}, "reward": -0.54} {"seed": 655, "task": "acde_hard", "difficulty": "hard", "step": 2, "state": {"patient_condition": "critical", "remaining_time_minutes": 11.0, "failed_hospitals": ["H4"], "visited_hospitals": ["H4"], "ambulance_status": "rerouting"}, "action": {"hospital_id": "H1", "policy_score": 0.19845202673062995, "strategy": "risk-aware policy + immediate-retry override"}, "outcome": {"status": "PARTIAL", "reason": "Critical deterioration managed temporarily; reroute still needed"}, "reward": 0.21} {"seed": 655, "task": "acde_hard", "difficulty": "hard", "step": 3, "state": {"patient_condition": "critical", "remaining_time_minutes": 11.0, "failed_hospitals": ["H4"], "visited_hospitals": ["H4", "H1"], "ambulance_status": "in_transit"}, "action": {"hospital_id": "H5", "policy_score": 0.4028299518385686, "strategy": "balanced policy + guided-exploration"}, "outcome": {"status": "ACCEPTED", "reason": "Patient stabilized after delayed admission"}, "reward": 0.86} {"seed": 755, "task": "acde_hard", "difficulty": "hard", "step": 1, "state": {"patient_condition": "critical", "remaining_time_minutes": 13.0, "failed_hospitals": [], "visited_hospitals": [], "ambulance_status": "en_route"}, "action": {"hospital_id": "H5", "policy_score": 0.32851089318299087, "strategy": "safe policy + critical triage"}, "outcome": {"status": "PARTIAL", "reason": "Admitted with delays: prolonged transfer strain, doctor delayed"}, "reward": 0.28500000000000003} {"seed": 755, "task": "acde_hard", "difficulty": "hard", "step": 2, "state": {"patient_condition": "critical", "remaining_time_minutes": 13.0, "failed_hospitals": [], "visited_hospitals": ["H5"], "ambulance_status": "in_transit"}, "action": {"hospital_id": "H5", "policy_score": 0.44142722677581125, "strategy": "balanced policy + anti-stupidity guard"}, "outcome": {"status": "REJECTED", "reason": "Condition became irreversible after delays"}, "reward": -0.81} {"seed": 755, "task": "acde_hard", "difficulty": "hard", "step": 3, "state": {"patient_condition": "critical", "remaining_time_minutes": 13.0, "failed_hospitals": ["H6"], "visited_hospitals": ["H5", "H6"], "ambulance_status": "rerouting"}, "action": {"hospital_id": "H3", "policy_score": 0.3138542681752489, "strategy": "risk-aware policy + anti-stupidity guard"}, "outcome": {"status": "REJECTED", "reason": "Condition became irreversible after delays"}, "reward": -0.5} {"seed": 755, "task": "acde_hard", "difficulty": "hard", "step": 4, "state": {"patient_condition": "critical", "remaining_time_minutes": 13.0, "failed_hospitals": ["H6", "H4"], "visited_hospitals": ["H5", "H6", "H4"], "ambulance_status": "rerouting"}, "action": {"hospital_id": "H2", "policy_score": 0.19976414401435783, "strategy": "risk-aware policy + anti-stupidity guard + immediate-retry override"}, "outcome": {"status": "REJECTED", "reason": "Hospital cannot admit: Hospital overloaded"}, "reward": -0.6} {"seed": 9202, "task": "acde_medium", "difficulty": "medium", "step": 1, "state": {"patient_condition": "critical", "remaining_time_minutes": 14.0, "failed_hospitals": [], "visited_hospitals": [], "ambulance_status": "en_route"}, "action": {"hospital_id": "H5", "policy_score": 0.48530638552484023, "strategy": "safe policy + critical triage"}, "outcome": {"status": "ACCEPTED", "reason": "Patient stabilized after delayed admission"}, "reward": 0.98} {"seed": 9302, "task": "acde_medium", "difficulty": "medium", "step": 1, "state": {"patient_condition": "serious", "remaining_time_minutes": 17.0, "failed_hospitals": [], "visited_hospitals": [], "ambulance_status": "en_route"}, "action": {"hospital_id": "H2", "policy_score": 0.41673697554506417, "strategy": "safe policy"}, "outcome": {"status": "PARTIAL", "reason": "Admitted with significant risk: ICU unavailable"}, "reward": 0.3} {"seed": 9302, "task": "acde_medium", "difficulty": "medium", "step": 2, "state": {"patient_condition": "serious", "remaining_time_minutes": 17.0, "failed_hospitals": [], "visited_hospitals": ["H2"], "ambulance_status": "in_transit"}, "action": {"hospital_id": "H2", "policy_score": 0.40967135148628897, "strategy": "balanced policy + anti-stupidity guard"}, "outcome": {"status": "REJECTED", "reason": "Condition became non-transferable during delay; immediate critical care failed"}, "reward": -0.6900000000000001} {"seed": 9402, "task": "acde_medium", "difficulty": "medium", "step": 1, "state": {"patient_condition": "serious", "remaining_time_minutes": 17.0, "failed_hospitals": [], "visited_hospitals": [], "ambulance_status": "en_route"}, "action": {"hospital_id": "H2", "policy_score": 0.3960095518495598, "strategy": "safe policy + anti-stupidity guard"}, "outcome": {"status": "REJECTED", "reason": "Hidden mismatch at arrival (wrong risky guess). Rerouting required."}, "reward": -0.56} {"seed": 9402, "task": "acde_medium", "difficulty": "medium", "step": 2, "state": {"patient_condition": "serious", "remaining_time_minutes": 17.0, "failed_hospitals": ["H2"], "visited_hospitals": ["H2"], "ambulance_status": "rerouting"}, "action": {"hospital_id": "H4", "policy_score": 0.08584411470837407, "strategy": "risk-aware policy"}, "outcome": {"status": "REJECTED", "reason": "Hidden mismatch at arrival (wrong risky guess). Rerouting required."}, "reward": -0.64} {"seed": 9402, "task": "acde_medium", "difficulty": "medium", "step": 3, "state": {"patient_condition": "unstable", "remaining_time_minutes": 17.0, "failed_hospitals": ["H2", "H4"], "visited_hospitals": ["H2", "H4"], "ambulance_status": "rerouting"}, "action": {"hospital_id": "H5", "policy_score": 0.01867167480101229, "strategy": "risk-aware policy"}, "outcome": {"status": "ACCEPTED", "reason": "Condition stabilized after progressive treatment"}, "reward": 0.6} {"seed": 9502, "task": "acde_medium", "difficulty": "medium", "step": 1, "state": {"patient_condition": "serious", "remaining_time_minutes": 17.0, "failed_hospitals": [], "visited_hospitals": [], "ambulance_status": "en_route"}, "action": {"hospital_id": "H5", "policy_score": 0.28498585360956263, "strategy": "safe policy + guided-exploration"}, "outcome": {"status": "PARTIAL", "reason": "Early rejection mitigated by emergency field stabilization"}, "reward": 0.25} {"seed": 9502, "task": "acde_medium", "difficulty": "medium", "step": 2, "state": {"patient_condition": "serious", "remaining_time_minutes": 17.0, "failed_hospitals": [], "visited_hospitals": ["H5"], "ambulance_status": "in_transit"}, "action": {"hospital_id": "H2", "policy_score": 0.31904193185133, "strategy": "balanced policy"}, "outcome": {"status": "REJECTED", "reason": "Hospital cannot admit: Hospital overloaded"}, "reward": -0.5} {"seed": 9502, "task": "acde_medium", "difficulty": "medium", "step": 3, "state": {"patient_condition": "serious", "remaining_time_minutes": 17.0, "failed_hospitals": ["H2"], "visited_hospitals": ["H5", "H2"], "ambulance_status": "rerouting"}, "action": {"hospital_id": "H3", "policy_score": 0.31539351789334324, "strategy": "risk-aware policy"}, "outcome": {"status": "REJECTED", "reason": "Condition became irreversible after delays"}, "reward": -0.5} {"seed": 9502, "task": "acde_medium", "difficulty": "medium", "step": 4, "state": {"patient_condition": "serious", "remaining_time_minutes": 17.0, "failed_hospitals": ["H2", "H3"], "visited_hospitals": ["H5", "H2", "H3"], "ambulance_status": "rerouting"}, "action": {"hospital_id": "H5", "policy_score": 0.454558717193104, "strategy": "risk-aware policy + anti-stupidity guard"}, "outcome": {"status": "PARTIAL", "reason": "Condition worsened but remains temporarily transferable"}, "reward": 0.19999999999999998} {"seed": 9602, "task": "acde_medium", "difficulty": "medium", "step": 1, "state": {"patient_condition": "critical", "remaining_time_minutes": 15.0, "failed_hospitals": [], "visited_hospitals": [], "ambulance_status": "en_route"}, "action": {"hospital_id": "H3", "policy_score": 0.4223243708627159, "strategy": "safe policy + critical triage + anti-stupidity guard"}, "outcome": {"status": "PARTIAL", "reason": "Early rejection mitigated by emergency field stabilization"}, "reward": 0.24999999999999997} {"seed": 9602, "task": "acde_medium", "difficulty": "medium", "step": 2, "state": {"patient_condition": "critical", "remaining_time_minutes": 15.0, "failed_hospitals": [], "visited_hospitals": ["H3"], "ambulance_status": "in_transit"}, "action": {"hospital_id": "H5", "policy_score": 0.25595629493272043, "strategy": "balanced policy + critical triage"}, "outcome": {"status": "ACCEPTED", "reason": "Patient stabilized after critical delay"}, "reward": 0.74} {"seed": 9702, "task": "acde_medium", "difficulty": "medium", "step": 1, "state": {"patient_condition": "serious", "remaining_time_minutes": 17.0, "failed_hospitals": [], "visited_hospitals": [], "ambulance_status": "en_route"}, "action": {"hospital_id": "H2", "policy_score": 0.3140054745170835, "strategy": "safe policy + anti-stupidity guard"}, "outcome": {"status": "PARTIAL", "reason": "Initial triage completed; transfer monitoring still required"}, "reward": 0.35} {"seed": 9702, "task": "acde_medium", "difficulty": "medium", "step": 2, "state": {"patient_condition": "serious", "remaining_time_minutes": 17.0, "failed_hospitals": [], "visited_hospitals": ["H2"], "ambulance_status": "in_transit"}, "action": {"hospital_id": "H5", "policy_score": 0.43016829360764575, "strategy": "balanced policy"}, "outcome": {"status": "ACCEPTED", "reason": "Patient stabilized after critical delay"}, "reward": 0.74} {"seed": 9802, "task": "acde_medium", "difficulty": "medium", "step": 1, "state": {"patient_condition": "critical", "remaining_time_minutes": 14.0, "failed_hospitals": [], "visited_hospitals": [], "ambulance_status": "en_route"}, "action": {"hospital_id": "H3", "policy_score": 0.4269883901781745, "strategy": "safe policy + critical triage"}, "outcome": {"status": "PARTIAL", "reason": "Admitted with delays: prolonged transfer strain, doctor delayed"}, "reward": 0.225} {"seed": 9802, "task": "acde_medium", "difficulty": "medium", "step": 2, "state": {"patient_condition": "unstable", "remaining_time_minutes": 14.0, "failed_hospitals": [], "visited_hospitals": ["H3"], "ambulance_status": "in_transit"}, "action": {"hospital_id": "H2", "policy_score": 0.4453677731108761, "strategy": "balanced policy + critical triage"}, "outcome": {"status": "REJECTED", "reason": "Condition became non-transferable during delay; immediate critical care failed"}, "reward": -0.5} {"seed": 9902, "task": "acde_medium", "difficulty": "medium", "step": 1, "state": {"patient_condition": "critical", "remaining_time_minutes": 14.0, "failed_hospitals": [], "visited_hospitals": [], "ambulance_status": "en_route"}, "action": {"hospital_id": "H2", "policy_score": 0.49935758401079444, "strategy": "safe policy"}, "outcome": {"status": "REJECTED", "reason": "Hospital cannot admit: ICU unavailable"}, "reward": -0.6200000000000001} {"seed": 9902, "task": "acde_medium", "difficulty": "medium", "step": 2, "state": {"patient_condition": "critical", "remaining_time_minutes": 14.0, "failed_hospitals": ["H2"], "visited_hospitals": ["H2"], "ambulance_status": "rerouting"}, "action": {"hospital_id": "H3", "policy_score": 0.12762547318481604, "strategy": "risk-aware policy"}, "outcome": {"status": "PARTIAL", "reason": "Admitted with delays: prolonged transfer strain, doctor delayed"}, "reward": 0.385} {"seed": 9902, "task": "acde_medium", "difficulty": "medium", "step": 3, "state": {"patient_condition": "unstable", "remaining_time_minutes": 14.0, "failed_hospitals": ["H2"], "visited_hospitals": ["H2", "H3"], "ambulance_status": "in_transit"}, "action": {"hospital_id": "H5", "policy_score": 0.18664305895372255, "strategy": "balanced policy + critical triage + guided-exploration"}, "outcome": {"status": "REJECTED", "reason": "Condition became non-transferable during delay; immediate critical care failed"}, "reward": -0.5800000000000001} {"seed": 10002, "task": "acde_medium", "difficulty": "medium", "step": 1, "state": {"patient_condition": "critical", "remaining_time_minutes": 15.0, "failed_hospitals": [], "visited_hospitals": [], "ambulance_status": "en_route"}, "action": {"hospital_id": "H5", "policy_score": 0.35892727881817577, "strategy": "safe policy + critical triage"}, "outcome": {"status": "REJECTED", "reason": "Hospital cannot admit: No specialist available"}, "reward": -0.5} {"seed": 10002, "task": "acde_medium", "difficulty": "medium", "step": 2, "state": {"patient_condition": "critical", "remaining_time_minutes": 15.0, "failed_hospitals": ["H5"], "visited_hospitals": ["H5"], "ambulance_status": "rerouting"}, "action": {"hospital_id": "H1", "policy_score": 0.08617280310972085, "strategy": "risk-aware policy"}, "outcome": {"status": "REJECTED", "reason": "Hospital cannot admit: ICU unavailable"}, "reward": -0.6200000000000001} {"seed": 10002, "task": "acde_medium", "difficulty": "medium", "step": 3, "state": {"patient_condition": "critical", "remaining_time_minutes": 15.0, "failed_hospitals": ["H5", "H1"], "visited_hospitals": ["H5", "H1"], "ambulance_status": "rerouting"}, "action": {"hospital_id": "H4", "policy_score": 0.08862584046555168, "strategy": "risk-aware policy + guided-exploration + anti-stupidity guard"}, "outcome": {"status": "REJECTED", "reason": "Hospital cannot admit: No specialist available"}, "reward": -0.5} {"seed": 10002, "task": "acde_medium", "difficulty": "medium", "step": 4, "state": {"patient_condition": "critical", "remaining_time_minutes": 15.0, "failed_hospitals": ["H5", "H1", "H3"], "visited_hospitals": ["H5", "H1", "H3"], "ambulance_status": "rerouting"}, "action": {"hospital_id": "H2", "policy_score": 0.0683360492286344, "strategy": "risk-aware policy + guided-exploration"}, "outcome": {"status": "ACCEPTED", "reason": "Emergency stabilization at last attempt"}, "reward": 0.72} {"seed": 10102, "task": "acde_medium", "difficulty": "medium", "step": 1, "state": {"patient_condition": "critical", "remaining_time_minutes": 15.0, "failed_hospitals": [], "visited_hospitals": [], "ambulance_status": "en_route"}, "action": {"hospital_id": "H1", "policy_score": 0.3560684982666949, "strategy": "safe policy + critical triage + anti-stupidity guard"}, "outcome": {"status": "PARTIAL", "reason": "Initial triage completed; transfer monitoring still required"}, "reward": 0.18999999999999997} {"seed": 10102, "task": "acde_medium", "difficulty": "medium", "step": 2, "state": {"patient_condition": "critical", "remaining_time_minutes": 15.0, "failed_hospitals": [], "visited_hospitals": ["H1"], "ambulance_status": "in_transit"}, "action": {"hospital_id": "H3", "policy_score": 0.4017344360450269, "strategy": "balanced policy + critical triage + anti-stupidity guard"}, "outcome": {"status": "REJECTED", "reason": "Condition became irreversible after delays"}, "reward": -0.5} {"seed": 10102, "task": "acde_medium", "difficulty": "medium", "step": 3, "state": {"patient_condition": "critical", "remaining_time_minutes": 15.0, "failed_hospitals": ["H2"], "visited_hospitals": ["H1", "H2"], "ambulance_status": "rerouting"}, "action": {"hospital_id": "H4", "policy_score": 0.07572774983524858, "strategy": "risk-aware policy + anti-stupidity guard + immediate-retry override"}, "outcome": {"status": "REJECTED", "reason": "Hospital cannot admit: ICU unavailable"}, "reward": -0.6200000000000001} {"seed": 10102, "task": "acde_medium", "difficulty": "medium", "step": 4, "state": {"patient_condition": "critical", "remaining_time_minutes": 15.0, "failed_hospitals": ["H2", "H1"], "visited_hospitals": ["H1", "H2"], "ambulance_status": "rerouting"}, "action": {"hospital_id": "H3", "policy_score": 0.4312081407580092, "strategy": "risk-aware policy"}, "outcome": {"status": "REJECTED", "reason": "Hidden mismatch at arrival (wrong risky guess). Rerouting required."}, "reward": -0.7600000000000001} {"seed": 9303, "task": "acde_hard", "difficulty": "hard", "step": 1, "state": {"patient_condition": "critical", "remaining_time_minutes": 11.0, "failed_hospitals": [], "visited_hospitals": [], "ambulance_status": "en_route"}, "action": {"hospital_id": "H1", "policy_score": 0.27869113840104875, "strategy": "safe policy + critical triage + anti-stupidity guard"}, "outcome": {"status": "REJECTED", "reason": "Condition became non-transferable during delay; immediate critical care failed"}, "reward": -0.46} {"seed": 9403, "task": "acde_hard", "difficulty": "hard", "step": 1, "state": {"patient_condition": "critical", "remaining_time_minutes": 11.0, "failed_hospitals": [], "visited_hospitals": [], "ambulance_status": "en_route"}, "action": {"hospital_id": "H6", "policy_score": 0.3449852127834684, "strategy": "safe policy + critical triage + anti-stupidity guard"}, "outcome": {"status": "REJECTED", "reason": "Hospital cannot admit: ICU unavailable, No specialist available"}, "reward": -0.42} {"seed": 9403, "task": "acde_hard", "difficulty": "hard", "step": 2, "state": {"patient_condition": "critical", "remaining_time_minutes": 11.0, "failed_hospitals": ["H6"], "visited_hospitals": ["H6"], "ambulance_status": "rerouting"}, "action": {"hospital_id": "H1", "policy_score": 0.3976308828873228, "strategy": "risk-aware policy"}, "outcome": {"status": "REJECTED", "reason": "Hospital cannot admit: ICU unavailable, No specialist available"}, "reward": -0.6} {"seed": 9403, "task": "acde_hard", "difficulty": "hard", "step": 3, "state": {"patient_condition": "critical", "remaining_time_minutes": 11.0, "failed_hospitals": ["H6", "H1"], "visited_hospitals": ["H6", "H1"], "ambulance_status": "rerouting"}, "action": {"hospital_id": "H4", "policy_score": 0.05541695618853306, "strategy": "risk-aware policy"}, "outcome": {"status": "REJECTED", "reason": "Hidden mismatch at arrival (wrong risky guess). Rerouting required."}, "reward": -0.86} {"seed": 9403, "task": "acde_hard", "difficulty": "hard", "step": 4, "state": {"patient_condition": "critical", "remaining_time_minutes": 11.0, "failed_hospitals": ["H6", "H1", "H5"], "visited_hospitals": ["H6", "H1", "H5"], "ambulance_status": "rerouting"}, "action": {"hospital_id": "H6", "policy_score": 0.23787382539411314, "strategy": "risk-aware policy + anti-stupidity guard + immediate-retry override"}, "outcome": {"status": "REJECTED", "reason": "Hospital cannot admit: ICU unavailable, No specialist available"}, "reward": -0.8900000000000001} {"seed": 9503, "task": "acde_hard", "difficulty": "hard", "step": 1, "state": {"patient_condition": "critical", "remaining_time_minutes": 11.0, "failed_hospitals": [], "visited_hospitals": [], "ambulance_status": "en_route"}, "action": {"hospital_id": "H1", "policy_score": 0.3835385248898784, "strategy": "safe policy + critical triage"}, "outcome": {"status": "REJECTED", "reason": "Unexpected complication at arrival"}, "reward": -0.6200000000000001} {"seed": 9503, "task": "acde_hard", "difficulty": "hard", "step": 2, "state": {"patient_condition": "critical", "remaining_time_minutes": 11.0, "failed_hospitals": ["H6"], "visited_hospitals": ["H6"], "ambulance_status": "rerouting"}, "action": {"hospital_id": "H5", "policy_score": 0.27385081617380297, "strategy": "risk-aware policy"}, "outcome": {"status": "PARTIAL", "reason": "Admitted with delays: prolonged transfer strain, doctor delayed"}, "reward": 0.225} {"seed": 9503, "task": "acde_hard", "difficulty": "hard", "step": 3, "state": {"patient_condition": "critical", "remaining_time_minutes": 11.0, "failed_hospitals": ["H6"], "visited_hospitals": ["H6", "H4"], "ambulance_status": "in_transit"}, "action": {"hospital_id": "H5", "policy_score": 0.39849999052008506, "strategy": "balanced policy + critical triage + guided-exploration"}, "outcome": {"status": "REJECTED", "reason": "Hospital cannot admit: ICU unavailable"}, "reward": -0.64} {"seed": 9503, "task": "acde_hard", "difficulty": "hard", "step": 4, "state": {"patient_condition": "critical", "remaining_time_minutes": 11.0, "failed_hospitals": ["H6", "H5"], "visited_hospitals": ["H6", "H4", "H5"], "ambulance_status": "rerouting"}, "action": {"hospital_id": "H4", "policy_score": 0.15913021041790704, "strategy": "risk-aware policy + anti-stupidity guard"}, "outcome": {"status": "ACCEPTED", "reason": "Emergency stabilization at last attempt"}, "reward": 0.2699999999999999} {"seed": 9603, "task": "acde_hard", "difficulty": "hard", "step": 1, "state": {"patient_condition": "critical", "remaining_time_minutes": 13.0, "failed_hospitals": [], "visited_hospitals": [], "ambulance_status": "en_route"}, "action": {"hospital_id": "H3", "policy_score": 0.41804040634190043, "strategy": "safe policy + critical triage"}, "outcome": {"status": "REJECTED", "reason": "Hospital cannot admit: Hospital overloaded"}, "reward": -0.5} {"seed": 9603, "task": "acde_hard", "difficulty": "hard", "step": 2, "state": {"patient_condition": "critical", "remaining_time_minutes": 13.0, "failed_hospitals": ["H3"], "visited_hospitals": ["H3"], "ambulance_status": "rerouting"}, "action": {"hospital_id": "H2", "policy_score": 0.08361801323640146, "strategy": "risk-aware policy"}, "outcome": {"status": "REJECTED", "reason": "Hospital cannot admit: ICU unavailable, No specialist available"}, "reward": -0.72} {"seed": 9603, "task": "acde_hard", "difficulty": "hard", "step": 3, "state": {"patient_condition": "critical", "remaining_time_minutes": 13.0, "failed_hospitals": ["H3", "H2"], "visited_hospitals": ["H3", "H2"], "ambulance_status": "rerouting"}, "action": {"hospital_id": "H4", "policy_score": 0.1663590514181034, "strategy": "risk-aware policy"}, "outcome": {"status": "REJECTED", "reason": "Condition relapsed after temporary stabilization"}, "reward": -0.6} {"seed": 9603, "task": "acde_hard", "difficulty": "hard", "step": 4, "state": {"patient_condition": "critical", "remaining_time_minutes": 13.0, "failed_hospitals": ["H3", "H2", "H4"], "visited_hospitals": ["H3", "H2", "H4"], "ambulance_status": "rerouting"}, "action": {"hospital_id": "H1", "policy_score": 0.10198491072137186, "strategy": "risk-aware policy"}, "outcome": {"status": "PARTIAL", "reason": "Temporary stabilization despite specialization mismatch"}, "reward": 0.375} {"seed": 9703, "task": "acde_hard", "difficulty": "hard", "step": 1, "state": {"patient_condition": "critical", "remaining_time_minutes": 13.0, "failed_hospitals": [], "visited_hospitals": [], "ambulance_status": "en_route"}, "action": {"hospital_id": "H2", "policy_score": 0.46182319304613434, "strategy": "safe policy"}, "outcome": {"status": "REJECTED", "reason": "Hospital cannot admit: No specialist available"}, "reward": -0.72} {"seed": 9703, "task": "acde_hard", "difficulty": "hard", "step": 2, "state": {"patient_condition": "critical", "remaining_time_minutes": 13.0, "failed_hospitals": ["H2"], "visited_hospitals": ["H2"], "ambulance_status": "rerouting"}, "action": {"hospital_id": "H1", "policy_score": 0.2119974306592057, "strategy": "risk-aware policy + anti-stupidity guard"}, "outcome": {"status": "REJECTED", "reason": "Hospital cannot admit: No specialist available"}, "reward": -0.56} {"seed": 9703, "task": "acde_hard", "difficulty": "hard", "step": 3, "state": {"patient_condition": "critical", "remaining_time_minutes": 13.0, "failed_hospitals": ["H2", "H1"], "visited_hospitals": ["H2", "H1"], "ambulance_status": "rerouting"}, "action": {"hospital_id": "H3", "policy_score": 0.4669928655285004, "strategy": "risk-aware policy"}, "outcome": {"status": "REJECTED", "reason": "Condition became non-transferable during delay; immediate critical care failed"}, "reward": -0.46} {"seed": 9803, "task": "acde_hard", "difficulty": "hard", "step": 1, "state": {"patient_condition": "critical", "remaining_time_minutes": 13.0, "failed_hospitals": [], "visited_hospitals": [], "ambulance_status": "en_route"}, "action": {"hospital_id": "H3", "policy_score": 0.2539369478705836, "strategy": "safe policy + critical triage"}, "outcome": {"status": "REJECTED", "reason": "Hidden mismatch at arrival (wrong risky guess). Rerouting required."}, "reward": -0.7200000000000001} {"seed": 9803, "task": "acde_hard", "difficulty": "hard", "step": 2, "state": {"patient_condition": "critical", "remaining_time_minutes": 13.0, "failed_hospitals": ["H6"], "visited_hospitals": ["H6"], "ambulance_status": "rerouting"}, "action": {"hospital_id": "H2", "policy_score": 0.30657021800952233, "strategy": "risk-aware policy + guided-exploration + immediate-retry override"}, "outcome": {"status": "PARTIAL", "reason": "Critical deterioration managed temporarily; reroute still needed"}, "reward": 0.21} {"seed": 9803, "task": "acde_hard", "difficulty": "hard", "step": 3, "state": {"patient_condition": "critical", "remaining_time_minutes": 13.0, "failed_hospitals": ["H6"], "visited_hospitals": ["H6", "H2"], "ambulance_status": "in_transit"}, "action": {"hospital_id": "H3", "policy_score": 0.42525600736881747, "strategy": "balanced policy + critical triage"}, "outcome": {"status": "REJECTED", "reason": "Condition became non-transferable during delay; immediate critical care failed"}, "reward": -0.64} {"seed": 9903, "task": "acde_hard", "difficulty": "hard", "step": 1, "state": {"patient_condition": "critical", "remaining_time_minutes": 11.0, "failed_hospitals": [], "visited_hospitals": [], "ambulance_status": "en_route"}, "action": {"hospital_id": "H1", "policy_score": 0.39423163284855206, "strategy": "safe policy + critical triage"}, "outcome": {"status": "REJECTED", "reason": "ICU got full moments before handover"}, "reward": -0.5800000000000001} {"seed": 9903, "task": "acde_hard", "difficulty": "hard", "step": 2, "state": {"patient_condition": "critical", "remaining_time_minutes": 11.0, "failed_hospitals": ["H5"], "visited_hospitals": ["H5"], "ambulance_status": "rerouting"}, "action": {"hospital_id": "H5", "policy_score": 0.08657546410187587, "strategy": "risk-aware policy + anti-stupidity guard + immediate-retry override"}, "outcome": {"status": "REJECTED", "reason": "Hidden mismatch at arrival (wrong risky guess). Rerouting required."}, "reward": -1.0} {"seed": 9903, "task": "acde_hard", "difficulty": "hard", "step": 3, "state": {"patient_condition": "critical", "remaining_time_minutes": 11.0, "failed_hospitals": ["H5", "H2"], "visited_hospitals": ["H5", "H2"], "ambulance_status": "rerouting"}, "action": {"hospital_id": "H1", "policy_score": 0.40132017475204806, "strategy": "risk-aware policy + anti-stupidity guard"}, "outcome": {"status": "REJECTED", "reason": "Hospital cannot admit: No specialist available, Hospital overloaded"}, "reward": -0.6200000000000001} {"seed": 9903, "task": "acde_hard", "difficulty": "hard", "step": 4, "state": {"patient_condition": "critical", "remaining_time_minutes": 11.0, "failed_hospitals": ["H5", "H2", "H1"], "visited_hospitals": ["H5", "H2", "H1"], "ambulance_status": "rerouting"}, "action": {"hospital_id": "H4", "policy_score": 0.09905721622445753, "strategy": "risk-aware policy + anti-stupidity guard"}, "outcome": {"status": "REJECTED", "reason": "Hidden mismatch at arrival (wrong risky guess). Rerouting required."}, "reward": -0.8} {"seed": 10003, "task": "acde_hard", "difficulty": "hard", "step": 1, "state": {"patient_condition": "critical", "remaining_time_minutes": 12.0, "failed_hospitals": [], "visited_hospitals": [], "ambulance_status": "en_route"}, "action": {"hospital_id": "H6", "policy_score": 0.4411994477093549, "strategy": "safe policy"}, "outcome": {"status": "PARTIAL", "reason": "Critical deterioration managed temporarily; reroute still needed"}, "reward": 0.16999999999999998} {"seed": 10003, "task": "acde_hard", "difficulty": "hard", "step": 2, "state": {"patient_condition": "critical", "remaining_time_minutes": 12.0, "failed_hospitals": [], "visited_hospitals": ["H6"], "ambulance_status": "in_transit"}, "action": {"hospital_id": "H5", "policy_score": 0.2522937363126481, "strategy": "balanced policy + critical triage"}, "outcome": {"status": "REJECTED", "reason": "Condition became irreversible after delays"}, "reward": -0.64} {"seed": 10003, "task": "acde_hard", "difficulty": "hard", "step": 3, "state": {"patient_condition": "critical", "remaining_time_minutes": 12.0, "failed_hospitals": ["H5"], "visited_hospitals": ["H6", "H5"], "ambulance_status": "rerouting"}, "action": {"hospital_id": "H6", "policy_score": 0.3937930160014168, "strategy": "risk-aware policy + anti-stupidity guard"}, "outcome": {"status": "REJECTED", "reason": "Hospital cannot admit: No specialist available"}, "reward": -0.87} {"seed": 10003, "task": "acde_hard", "difficulty": "hard", "step": 4, "state": {"patient_condition": "critical", "remaining_time_minutes": 12.0, "failed_hospitals": ["H5", "H1"], "visited_hospitals": ["H6", "H5", "H1"], "ambulance_status": "rerouting"}, "action": {"hospital_id": "H2", "policy_score": 0.23752867912363795, "strategy": "risk-aware policy"}, "outcome": {"status": "PARTIAL", "reason": "Condition worsened but remains temporarily transferable"}, "reward": 0.21} {"seed": 10103, "task": "acde_hard", "difficulty": "hard", "step": 1, "state": {"patient_condition": "critical", "remaining_time_minutes": 13.0, "failed_hospitals": [], "visited_hospitals": [], "ambulance_status": "en_route"}, "action": {"hospital_id": "H2", "policy_score": 0.39835963727950563, "strategy": "safe policy + critical triage"}, "outcome": {"status": "REJECTED", "reason": "Hospital cannot admit: No specialist available"}, "reward": -0.46} {"seed": 10103, "task": "acde_hard", "difficulty": "hard", "step": 2, "state": {"patient_condition": "critical", "remaining_time_minutes": 13.0, "failed_hospitals": ["H2"], "visited_hospitals": ["H2"], "ambulance_status": "rerouting"}, "action": {"hospital_id": "H3", "policy_score": 0.3338284686762355, "strategy": "risk-aware policy + guided-exploration"}, "outcome": {"status": "REJECTED", "reason": "Hospital cannot admit: ICU unavailable, No specialist available"}, "reward": -0.54} {"seed": 10103, "task": "acde_hard", "difficulty": "hard", "step": 3, "state": {"patient_condition": "critical", "remaining_time_minutes": 13.0, "failed_hospitals": ["H2", "H3"], "visited_hospitals": ["H2", "H3"], "ambulance_status": "rerouting"}, "action": {"hospital_id": "H6", "policy_score": 0.10828579019789498, "strategy": "risk-aware policy"}, "outcome": {"status": "REJECTED", "reason": "Condition became non-transferable during delay; immediate critical care failed"}, "reward": -0.72} {"seed": 10203, "task": "acde_hard", "difficulty": "hard", "step": 1, "state": {"patient_condition": "critical", "remaining_time_minutes": 13.0, "failed_hospitals": [], "visited_hospitals": [], "ambulance_status": "en_route"}, "action": {"hospital_id": "H2", "policy_score": 0.14471080971641598, "strategy": "safe policy"}, "outcome": {"status": "REJECTED", "reason": "Hospital cannot admit: Hospital overloaded"}, "reward": -0.72} {"seed": 10203, "task": "acde_hard", "difficulty": "hard", "step": 2, "state": {"patient_condition": "critical", "remaining_time_minutes": 13.0, "failed_hospitals": ["H2"], "visited_hospitals": ["H2"], "ambulance_status": "rerouting"}, "action": {"hospital_id": "H6", "policy_score": 0.12247810570775391, "strategy": "risk-aware policy + guided-exploration"}, "outcome": {"status": "REJECTED", "reason": "Hospital cannot admit: ICU unavailable"}, "reward": -0.66} {"seed": 10203, "task": "acde_hard", "difficulty": "hard", "step": 3, "state": {"patient_condition": "critical", "remaining_time_minutes": 13.0, "failed_hospitals": ["H2", "H6"], "visited_hospitals": ["H2", "H6"], "ambulance_status": "rerouting"}, "action": {"hospital_id": "H3", "policy_score": 0.1255652867289264, "strategy": "risk-aware policy"}, "outcome": {"status": "PARTIAL", "reason": "Critical deterioration managed temporarily; reroute still needed"}, "reward": 0.27} {"seed": 10203, "task": "acde_hard", "difficulty": "hard", "step": 4, "state": {"patient_condition": "critical", "remaining_time_minutes": 13.0, "failed_hospitals": ["H2", "H6"], "visited_hospitals": ["H2", "H6", "H3"], "ambulance_status": "in_transit"}, "action": {"hospital_id": "H1", "policy_score": 0.0995574242686072, "strategy": "balanced policy + critical triage + anti-stupidity guard"}, "outcome": {"status": "REJECTED", "reason": "Condition became irreversible after delays"}, "reward": -0.7000000000000001} {"seed": 9101, "task": "acde_easy", "difficulty": "easy", "step": 1, "state": {"patient_condition": "serious", "remaining_time_minutes": 18.0, "failed_hospitals": [], "visited_hospitals": [], "ambulance_status": "en_route"}, "action": {"hospital_id": "H3", "policy_score": 0.34053714087776576, "strategy": "safe policy"}, "outcome": {"status": "PARTIAL", "reason": "Admitted with significant risk: No specialist available"}, "reward": 0.33999999999999997} {"seed": 9101, "task": "acde_easy", "difficulty": "easy", "step": 2, "state": {"patient_condition": "serious", "remaining_time_minutes": 18.0, "failed_hospitals": [], "visited_hospitals": ["H3"], "ambulance_status": "in_transit"}, "action": {"hospital_id": "H1", "policy_score": 0.3630487701168095, "strategy": "balanced policy"}, "outcome": {"status": "REJECTED", "reason": "Hidden mismatch at arrival (wrong risky guess). Rerouting required."}, "reward": -0.6} {"seed": 9101, "task": "acde_easy", "difficulty": "easy", "step": 3, "state": {"patient_condition": "serious", "remaining_time_minutes": 18.0, "failed_hospitals": ["H1"], "visited_hospitals": ["H3", "H1"], "ambulance_status": "rerouting"}, "action": {"hospital_id": "H3", "policy_score": 0.4547255455903119, "strategy": "risk-aware policy + anti-stupidity guard"}, "outcome": {"status": "REJECTED", "reason": "Hospital cannot admit: Hospital overloaded"}, "reward": -0.61} {"seed": 9201, "task": "acde_easy", "difficulty": "easy", "step": 1, "state": {"patient_condition": "serious", "remaining_time_minutes": 18.0, "failed_hospitals": [], "visited_hospitals": [], "ambulance_status": "en_route"}, "action": {"hospital_id": "H1", "policy_score": 0.33669905885582807, "strategy": "safe policy + anti-stupidity guard"}, "outcome": {"status": "ACCEPTED", "reason": "Patient admitted and treatment began"}, "reward": 1.0} {"seed": 9301, "task": "acde_easy", "difficulty": "easy", "step": 1, "state": {"patient_condition": "serious", "remaining_time_minutes": 18.0, "failed_hospitals": [], "visited_hospitals": [], "ambulance_status": "en_route"}, "action": {"hospital_id": "H1", "policy_score": 0.25939993949760737, "strategy": "safe policy + anti-stupidity guard"}, "outcome": {"status": "PARTIAL", "reason": "Critical deterioration managed temporarily; reroute still needed"}, "reward": 0.33} {"seed": 9301, "task": "acde_easy", "difficulty": "easy", "step": 2, "state": {"patient_condition": "serious", "remaining_time_minutes": 18.0, "failed_hospitals": [], "visited_hospitals": ["H1"], "ambulance_status": "in_transit"}, "action": {"hospital_id": "H4", "policy_score": 0.26991339609203696, "strategy": "balanced policy"}, "outcome": {"status": "ACCEPTED", "reason": "Patient stabilized after delayed admission"}, "reward": 0.96} {"seed": 9401, "task": "acde_easy", "difficulty": "easy", "step": 1, "state": {"patient_condition": "serious", "remaining_time_minutes": 20.0, "failed_hospitals": [], "visited_hospitals": [], "ambulance_status": "en_route"}, "action": {"hospital_id": "H1", "policy_score": 0.37636782794579104, "strategy": "safe policy"}, "outcome": {"status": "PARTIAL", "reason": "Admitted with significant risk: No specialist available"}, "reward": 0.38} {"seed": 9401, "task": "acde_easy", "difficulty": "easy", "step": 2, "state": {"patient_condition": "serious", "remaining_time_minutes": 20.0, "failed_hospitals": [], "visited_hospitals": ["H1"], "ambulance_status": "in_transit"}, "action": {"hospital_id": "H3", "policy_score": 0.29172196271161144, "strategy": "balanced policy"}, "outcome": {"status": "ACCEPTED", "reason": "Patient stabilized after delayed admission"}, "reward": 0.96} {"seed": 9501, "task": "acde_easy", "difficulty": "easy", "step": 1, "state": {"patient_condition": "serious", "remaining_time_minutes": 20.0, "failed_hospitals": [], "visited_hospitals": [], "ambulance_status": "en_route"}, "action": {"hospital_id": "H1", "policy_score": 0.34088040717180834, "strategy": "safe policy"}, "outcome": {"status": "ACCEPTED", "reason": "Patient admitted and treatment began"}, "reward": 1.0} {"seed": 9601, "task": "acde_easy", "difficulty": "easy", "step": 1, "state": {"patient_condition": "serious", "remaining_time_minutes": 18.0, "failed_hospitals": [], "visited_hospitals": [], "ambulance_status": "en_route"}, "action": {"hospital_id": "H1", "policy_score": 0.37299762346645954, "strategy": "safe policy"}, "outcome": {"status": "ACCEPTED", "reason": "Patient admitted and treatment began"}, "reward": 1.0} {"seed": 9701, "task": "acde_easy", "difficulty": "easy", "step": 1, "state": {"patient_condition": "critical", "remaining_time_minutes": 16.0, "failed_hospitals": [], "visited_hospitals": [], "ambulance_status": "en_route"}, "action": {"hospital_id": "H2", "policy_score": 0.3332734973156262, "strategy": "safe policy + critical triage"}, "outcome": {"status": "ACCEPTED", "reason": "Patient admitted and treatment began"}, "reward": 1.0} {"seed": 9801, "task": "acde_easy", "difficulty": "easy", "step": 1, "state": {"patient_condition": "critical", "remaining_time_minutes": 16.0, "failed_hospitals": [], "visited_hospitals": [], "ambulance_status": "en_route"}, "action": {"hospital_id": "H2", "policy_score": 0.35013506901450886, "strategy": "safe policy + critical triage + guided-exploration"}, "outcome": {"status": "ACCEPTED", "reason": "Patient admitted and treatment began"}, "reward": 1.0} {"seed": 9901, "task": "acde_easy", "difficulty": "easy", "step": 1, "state": {"patient_condition": "serious", "remaining_time_minutes": 18.0, "failed_hospitals": [], "visited_hospitals": [], "ambulance_status": "en_route"}, "action": {"hospital_id": "H3", "policy_score": 0.2993531953946026, "strategy": "safe policy"}, "outcome": {"status": "ACCEPTED", "reason": "Patient admitted and treatment began"}, "reward": 1.0} {"seed": 10001, "task": "acde_easy", "difficulty": "easy", "step": 1, "state": {"patient_condition": "serious", "remaining_time_minutes": 20.0, "failed_hospitals": [], "visited_hospitals": [], "ambulance_status": "en_route"}, "action": {"hospital_id": "H3", "policy_score": 0.2785521192526889, "strategy": "safe policy"}, "outcome": {"status": "ACCEPTED", "reason": "Patient admitted and treatment began"}, "reward": 1.0} {"seed": 111, "task": "acde_easy", "difficulty": "easy", "step": 1, "state": {"patient_condition": "serious", "remaining_time_minutes": 20.0, "failed_hospitals": [], "visited_hospitals": [], "ambulance_status": "en_route"}, "action": {"hospital_id": "H1", "policy_score": 0.3343328223771947, "strategy": "safe policy"}, "outcome": {"status": "ACCEPTED", "reason": "Patient stabilized after delayed admission"}, "reward": 0.98} {"seed": 9202, "task": "acde_medium", "difficulty": "medium", "step": 1, "state": {"patient_condition": "critical", "remaining_time_minutes": 14.0, "failed_hospitals": [], "visited_hospitals": [], "ambulance_status": "en_route"}, "action": {"hospital_id": "H5", "policy_score": 0.4854681914076394, "strategy": "best-route retain"}, "outcome": {"status": "ACCEPTED", "reason": "Patient stabilized after delayed admission"}, "reward": 0.98} {"seed": 9303, "task": "acde_hard", "difficulty": "hard", "step": 1, "state": {"patient_condition": "critical", "remaining_time_minutes": 11.0, "failed_hospitals": [], "visited_hospitals": [], "ambulance_status": "en_route"}, "action": {"hospital_id": "H1", "policy_score": 0.27850913344818784, "strategy": "best-route retain"}, "outcome": {"status": "REJECTED", "reason": "Condition became non-transferable during delay; immediate critical care failed"}, "reward": -0.46} {"seed": 777, "task": "acde_easy", "difficulty": "easy", "step": 1, "state": {"patient_condition": "critical", "remaining_time_minutes": 16.0, "failed_hospitals": [], "visited_hospitals": [], "ambulance_status": "en_route"}, "action": {"hospital_id": "H4", "policy_score": 0.3882903414996688, "strategy": "safe policy + critical triage"}, "outcome": {"status": "ACCEPTED", "reason": "Patient admitted and treatment began"}, "reward": 0.96} {"seed": 777, "task": "acde_easy", "difficulty": "easy", "step": 1, "state": {"patient_condition": "critical", "remaining_time_minutes": 16.0, "failed_hospitals": [], "visited_hospitals": [], "ambulance_status": "en_route"}, "action": {"hospital_id": "H4", "policy_score": 0.38933519435395464, "strategy": "best-route retain"}, "outcome": {"status": "ACCEPTED", "reason": "Patient admitted and treatment began"}, "reward": 0.96} {"seed": 888, "task": "acde_easy", "difficulty": "easy", "step": 1, "state": {"patient_condition": "serious", "remaining_time_minutes": 20.0, "failed_hospitals": [], "visited_hospitals": [], "ambulance_status": "en_route"}, "action": {"hospital_id": "H3", "policy_score": 0.3726765110796017, "strategy": "safe policy + guided-exploration + anti-stupidity guard"}, "outcome": {"status": "ACCEPTED", "reason": "Patient admitted and treatment began"}, "reward": 1.0} {"seed": 889, "task": "acde_medium", "difficulty": "medium", "step": 1, "state": {"patient_condition": "critical", "remaining_time_minutes": 14.0, "failed_hospitals": [], "visited_hospitals": [], "ambulance_status": "en_route"}, "action": {"hospital_id": "H2", "policy_score": 0.47455879649509997, "strategy": "safe policy + critical triage"}, "outcome": {"status": "PARTIAL", "reason": "Admitted with delays: patient worsened during transfer"}, "reward": 0.44} {"seed": 889, "task": "acde_medium", "difficulty": "medium", "step": 2, "state": {"patient_condition": "critical", "remaining_time_minutes": 14.0, "failed_hospitals": [], "visited_hospitals": ["H2"], "ambulance_status": "in_transit"}, "action": {"hospital_id": "H2", "policy_score": 0.4799791381370336, "strategy": "balanced policy + anti-stupidity guard"}, "outcome": {"status": "REJECTED", "reason": "Hospital cannot admit: No specialist available"}, "reward": -0.65} {"seed": 889, "task": "acde_medium", "difficulty": "medium", "step": 3, "state": {"patient_condition": "critical", "remaining_time_minutes": 14.0, "failed_hospitals": ["H2"], "visited_hospitals": ["H2"], "ambulance_status": "rerouting"}, "action": {"hospital_id": "H3", "policy_score": 0.4794517835786907, "strategy": "risk-aware policy"}, "outcome": {"status": "REJECTED", "reason": "Hospital cannot admit: ICU unavailable, No specialist available"}, "reward": -0.45999999999999996} {"seed": 889, "task": "acde_medium", "difficulty": "medium", "step": 4, "state": {"patient_condition": "critical", "remaining_time_minutes": 14.0, "failed_hospitals": ["H2", "H4"], "visited_hospitals": ["H2", "H4"], "ambulance_status": "rerouting"}, "action": {"hospital_id": "H2", "policy_score": 0.036793412285148736, "strategy": "risk-aware policy + immediate-retry override"}, "outcome": {"status": "ACCEPTED", "reason": "Patient stabilized after critical delay"}, "reward": 0.43} {"seed": 890, "task": "acde_hard", "difficulty": "hard", "step": 1, "state": {"patient_condition": "critical", "remaining_time_minutes": 11.0, "failed_hospitals": [], "visited_hospitals": [], "ambulance_status": "en_route"}, "action": {"hospital_id": "H1", "policy_score": 0.32912422400108593, "strategy": "safe policy + critical triage + guided-exploration + anti-stupidity guard"}, "outcome": {"status": "REJECTED", "reason": "Hospital cannot admit: ICU unavailable"}, "reward": -0.6} {"seed": 890, "task": "acde_hard", "difficulty": "hard", "step": 2, "state": {"patient_condition": "critical", "remaining_time_minutes": 11.0, "failed_hospitals": ["H1"], "visited_hospitals": ["H1"], "ambulance_status": "rerouting"}, "action": {"hospital_id": "H3", "policy_score": 0.3101395732431066, "strategy": "risk-aware policy"}, "outcome": {"status": "REJECTED", "reason": "Hospital cannot admit: ICU unavailable"}, "reward": -0.6} {"seed": 890, "task": "acde_hard", "difficulty": "hard", "step": 3, "state": {"patient_condition": "critical", "remaining_time_minutes": 11.0, "failed_hospitals": ["H1", "H3"], "visited_hospitals": ["H1", "H3"], "ambulance_status": "rerouting"}, "action": {"hospital_id": "H5", "policy_score": 0.3564022087214262, "strategy": "risk-aware policy + anti-stupidity guard"}, "outcome": {"status": "REJECTED", "reason": "Hidden mismatch at arrival (wrong risky guess). Rerouting required."}, "reward": -0.7200000000000001} {"seed": 890, "task": "acde_hard", "difficulty": "hard", "step": 4, "state": {"patient_condition": "critical", "remaining_time_minutes": 11.0, "failed_hospitals": ["H1", "H3", "H6"], "visited_hospitals": ["H1", "H3", "H6"], "ambulance_status": "rerouting"}, "action": {"hospital_id": "H3", "policy_score": 0.07634194594284169, "strategy": "risk-aware policy + immediate-retry override"}, "outcome": {"status": "PARTIAL", "reason": "Admitted with significant risk: No specialist available"}, "reward": -0.21000000000000002} {"seed": 9303, "task": "acde_hard", "difficulty": "hard", "step": 1, "state": {"patient_condition": "critical", "remaining_time_minutes": 11.0, "failed_hospitals": [], "visited_hospitals": [], "ambulance_status": "en_route"}, "action": {"hospital_id": "H6", "policy_score": 0.27850913344818784, "strategy": "combination search step-1 alt-1"}, "outcome": {"status": "REJECTED", "reason": "Condition became non-transferable during delay; immediate critical care failed"}, "reward": 0.07} {"seed": 9303, "task": "acde_hard", "difficulty": "hard", "step": 1, "state": {"patient_condition": "critical", "remaining_time_minutes": 11.0, "failed_hospitals": [], "visited_hospitals": [], "ambulance_status": "en_route"}, "action": {"hospital_id": "H1", "policy_score": 0.2842462077888691, "strategy": "combination search step-1 alt-2 + anti-stupidity guard"}, "outcome": {"status": "REJECTED", "reason": "Condition became non-transferable during delay; immediate critical care failed"}, "reward": 0.11} {"seed": 9403, "task": "acde_hard", "difficulty": "hard", "step": 1, "state": {"patient_condition": "critical", "remaining_time_minutes": 11.0, "failed_hospitals": [], "visited_hospitals": [], "ambulance_status": "en_route"}, "action": {"hospital_id": "H6", "policy_score": 0.3505613368524105, "strategy": "best-route retain"}, "outcome": {"status": "REJECTED", "reason": "Hospital cannot admit: ICU unavailable, No specialist available"}, "reward": 0.14} {"seed": 9403, "task": "acde_hard", "difficulty": "hard", "step": 2, "state": {"patient_condition": "critical", "remaining_time_minutes": 11.0, "failed_hospitals": ["H6"], "visited_hospitals": ["H6"], "ambulance_status": "rerouting"}, "action": {"hospital_id": "H1", "policy_score": 0.3976308820709832, "strategy": "risk-aware policy"}, "outcome": {"status": "REJECTED", "reason": "Hospital cannot admit: ICU unavailable, No specialist available"}, "reward": 0.0} {"seed": 9403, "task": "acde_hard", "difficulty": "hard", "step": 3, "state": {"patient_condition": "critical", "remaining_time_minutes": 11.0, "failed_hospitals": ["H6", "H1"], "visited_hospitals": ["H6", "H1"], "ambulance_status": "rerouting"}, "action": {"hospital_id": "H4", "policy_score": 0.05541697635438271, "strategy": "risk-aware policy"}, "outcome": {"status": "REJECTED", "reason": "Hidden mismatch at arrival (wrong risky guess). Rerouting required."}, "reward": 0.0} {"seed": 9403, "task": "acde_hard", "difficulty": "hard", "step": 4, "state": {"patient_condition": "critical", "remaining_time_minutes": 11.0, "failed_hospitals": ["H6", "H1", "H5"], "visited_hospitals": ["H6", "H1", "H5"], "ambulance_status": "rerouting"}, "action": {"hospital_id": "H6", "policy_score": 0.23787382539411314, "strategy": "risk-aware policy + anti-stupidity guard + immediate-retry override"}, "outcome": {"status": "REJECTED", "reason": "Hospital cannot admit: ICU unavailable, No specialist available"}, "reward": 0.0} {"seed": 9503, "task": "acde_hard", "difficulty": "hard", "step": 1, "state": {"patient_condition": "critical", "remaining_time_minutes": 11.0, "failed_hospitals": [], "visited_hospitals": [], "ambulance_status": "en_route"}, "action": {"hospital_id": "H1", "policy_score": 0.38320155547799756, "strategy": "best-route retain"}, "outcome": {"status": "REJECTED", "reason": "Unexpected complication at arrival"}, "reward": 0.0} {"seed": 9503, "task": "acde_hard", "difficulty": "hard", "step": 2, "state": {"patient_condition": "critical", "remaining_time_minutes": 11.0, "failed_hospitals": ["H6"], "visited_hospitals": ["H6"], "ambulance_status": "rerouting"}, "action": {"hospital_id": "H5", "policy_score": 0.3145806122254421, "strategy": "risk-aware policy"}, "outcome": {"status": "PARTIAL", "reason": "Admitted with delays: prolonged transfer strain, doctor delayed"}, "reward": 0.23750000000000002} {"seed": 9503, "task": "acde_hard", "difficulty": "hard", "step": 3, "state": {"patient_condition": "critical", "remaining_time_minutes": 11.0, "failed_hospitals": ["H6"], "visited_hospitals": ["H6", "H4"], "ambulance_status": "in_transit"}, "action": {"hospital_id": "H5", "policy_score": 0.39849999384612406, "strategy": "best-route retain"}, "outcome": {"status": "REJECTED", "reason": "Hospital cannot admit: ICU unavailable"}, "reward": 0.0} {"seed": 9503, "task": "acde_hard", "difficulty": "hard", "step": 4, "state": {"patient_condition": "critical", "remaining_time_minutes": 11.0, "failed_hospitals": ["H6", "H5"], "visited_hospitals": ["H6", "H4", "H5"], "ambulance_status": "rerouting"}, "action": {"hospital_id": "H4", "policy_score": 0.15913021041790704, "strategy": "risk-aware policy + anti-stupidity guard"}, "outcome": {"status": "ACCEPTED", "reason": "Emergency stabilization at last attempt"}, "reward": 0.20359999999999998} {"seed": 901, "task": "acde_easy", "difficulty": "easy", "step": 1, "state": {"patient_condition": "serious", "remaining_time_minutes": 20.0, "failed_hospitals": [], "visited_hospitals": [], "ambulance_status": "en_route"}, "action": {"hospital_id": "H3", "policy_score": 0.3620940130172604, "strategy": "safe policy"}, "outcome": {"status": "PARTIAL", "reason": "Admitted with delays: prolonged transfer strain"}, "reward": 0.44000000000000006} {"seed": 901, "task": "acde_easy", "difficulty": "easy", "step": 2, "state": {"patient_condition": "stable", "remaining_time_minutes": 20.0, "failed_hospitals": [], "visited_hospitals": ["H3"], "ambulance_status": "in_transit"}, "action": {"hospital_id": "H1", "policy_score": 0.390184325543089, "strategy": "balanced policy"}, "outcome": {"status": "REJECTED", "reason": "Hidden mismatch at arrival (wrong risky guess). Rerouting required."}, "reward": 0.0} {"seed": 901, "task": "acde_easy", "difficulty": "easy", "step": 3, "state": {"patient_condition": "stable", "remaining_time_minutes": 20.0, "failed_hospitals": ["H1"], "visited_hospitals": ["H3", "H1"], "ambulance_status": "rerouting"}, "action": {"hospital_id": "H3", "policy_score": 0.46359119957826816, "strategy": "risk-aware policy + anti-stupidity guard"}, "outcome": {"status": "ACCEPTED", "reason": "Patient stabilized after delayed admission"}, "reward": 0.7180000000000001} {"seed": 902, "task": "acde_medium", "difficulty": "medium", "step": 1, "state": {"patient_condition": "critical", "remaining_time_minutes": 15.0, "failed_hospitals": [], "visited_hospitals": [], "ambulance_status": "en_route"}, "action": {"hospital_id": "H3", "policy_score": 0.4175454985810999, "strategy": "safe policy + critical triage"}, "outcome": {"status": "REJECTED", "reason": "Unexpected complication at arrival"}, "reward": 0.07} {"seed": 902, "task": "acde_medium", "difficulty": "medium", "step": 2, "state": {"patient_condition": "critical", "remaining_time_minutes": 15.0, "failed_hospitals": ["H3"], "visited_hospitals": ["H3"], "ambulance_status": "rerouting"}, "action": {"hospital_id": "H1", "policy_score": 0.3460450883175071, "strategy": "risk-aware policy"}, "outcome": {"status": "REJECTED", "reason": "Condition relapsed after temporary stabilization"}, "reward": 0.11} {"seed": 902, "task": "acde_medium", "difficulty": "medium", "step": 3, "state": {"patient_condition": "critical", "remaining_time_minutes": 15.0, "failed_hospitals": ["H3", "H2"], "visited_hospitals": ["H3", "H2"], "ambulance_status": "rerouting"}, "action": {"hospital_id": "H5", "policy_score": 0.2607270795377634, "strategy": "risk-aware policy"}, "outcome": {"status": "REJECTED", "reason": "Hospital cannot admit: ICU unavailable"}, "reward": 0.0} {"seed": 902, "task": "acde_medium", "difficulty": "medium", "step": 4, "state": {"patient_condition": "critical", "remaining_time_minutes": 15.0, "failed_hospitals": ["H3", "H2", "H5"], "visited_hospitals": ["H3", "H2", "H5"], "ambulance_status": "rerouting"}, "action": {"hospital_id": "H1", "policy_score": 0.4218614428252817, "strategy": "risk-aware policy + anti-stupidity guard"}, "outcome": {"status": "ACCEPTED", "reason": "Emergency stabilization at last attempt"}, "reward": 0.32400000000000007} {"seed": 903, "task": "acde_hard", "difficulty": "hard", "step": 1, "state": {"patient_condition": "critical", "remaining_time_minutes": 12.0, "failed_hospitals": [], "visited_hospitals": [], "ambulance_status": "en_route"}, "action": {"hospital_id": "H2", "policy_score": 0.19802025980959623, "strategy": "safe policy"}, "outcome": {"status": "REJECTED", "reason": "Hidden mismatch at arrival (wrong risky guess). Rerouting required."}, "reward": 0.0} {"seed": 903, "task": "acde_hard", "difficulty": "hard", "step": 2, "state": {"patient_condition": "critical", "remaining_time_minutes": 12.0, "failed_hospitals": ["H2"], "visited_hospitals": ["H2"], "ambulance_status": "rerouting"}, "action": {"hospital_id": "H5", "policy_score": 0.11018241263788522, "strategy": "risk-aware policy + guided-exploration"}, "outcome": {"status": "PARTIAL", "reason": "Temporary stabilization despite specialization mismatch"}, "reward": 0.24250000000000002} {"seed": 903, "task": "acde_hard", "difficulty": "hard", "step": 3, "state": {"patient_condition": "critical", "remaining_time_minutes": 12.0, "failed_hospitals": ["H2"], "visited_hospitals": ["H2", "H5"], "ambulance_status": "in_transit"}, "action": {"hospital_id": "H1", "policy_score": 0.0961459054777727, "strategy": "balanced policy + critical triage + guided-exploration + anti-stupidity guard"}, "outcome": {"status": "REJECTED", "reason": "Condition became irreversible after delays"}, "reward": 0.0} {"seed": 903, "task": "acde_hard", "difficulty": "hard", "step": 4, "state": {"patient_condition": "critical", "remaining_time_minutes": 12.0, "failed_hospitals": ["H2", "H1"], "visited_hospitals": ["H2", "H5", "H1"], "ambulance_status": "rerouting"}, "action": {"hospital_id": "H3", "policy_score": 0.17607547693402878, "strategy": "risk-aware policy"}, "outcome": {"status": "REJECTED", "reason": "Condition became irreversible after delays"}, "reward": 0.07} {"seed": 202601, "task": "acde_easy", "difficulty": "easy", "step": 1, "state": {"patient_condition": "critical", "remaining_time_minutes": 16.0, "failed_hospitals": [], "visited_hospitals": [], "ambulance_status": "en_route"}, "action": {"hospital_id": "H1", "policy_score": 0.4397018166604085, "strategy": "safe policy + critical triage"}, "outcome": {"status": "ACCEPTED", "reason": "Patient admitted and treatment began"}, "reward": 0.8500000000000001} {"seed": 202602, "task": "acde_medium", "difficulty": "medium", "step": 1, "state": {"patient_condition": "serious", "remaining_time_minutes": 17.0, "failed_hospitals": [], "visited_hospitals": [], "ambulance_status": "en_route"}, "action": {"hospital_id": "H2", "policy_score": 0.3187639889034849, "strategy": "safe policy"}, "outcome": {"status": "PARTIAL", "reason": "Early rejection mitigated by emergency field stabilization"}, "reward": 0.30500000000000005} {"seed": 202602, "task": "acde_medium", "difficulty": "medium", "step": 2, "state": {"patient_condition": "serious", "remaining_time_minutes": 17.0, "failed_hospitals": [], "visited_hospitals": ["H2"], "ambulance_status": "in_transit"}, "action": {"hospital_id": "H3", "policy_score": 0.4255811121284265, "strategy": "balanced policy"}, "outcome": {"status": "REJECTED", "reason": "Hospital cannot admit: ICU unavailable"}, "reward": 0.11} {"seed": 202602, "task": "acde_medium", "difficulty": "medium", "step": 3, "state": {"patient_condition": "serious", "remaining_time_minutes": 17.0, "failed_hospitals": ["H5"], "visited_hospitals": ["H2", "H5"], "ambulance_status": "rerouting"}, "action": {"hospital_id": "H2", "policy_score": 0.2822407131999345, "strategy": "risk-aware policy + anti-stupidity guard + immediate-retry override"}, "outcome": {"status": "ACCEPTED", "reason": "Patient stabilized after critical delay"}, "reward": 0.5156000000000001} {"seed": 202603, "task": "acde_hard", "difficulty": "hard", "step": 1, "state": {"patient_condition": "critical", "remaining_time_minutes": 12.0, "failed_hospitals": [], "visited_hospitals": [], "ambulance_status": "en_route"}, "action": {"hospital_id": "H2", "policy_score": 0.3966680995461216, "strategy": "safe policy + critical triage + guided-exploration + anti-stupidity guard"}, "outcome": {"status": "PARTIAL", "reason": "Early rejection mitigated by emergency field stabilization"}, "reward": 0.17500000000000002} {"seed": 202603, "task": "acde_hard", "difficulty": "hard", "step": 2, "state": {"patient_condition": "critical", "remaining_time_minutes": 12.0, "failed_hospitals": [], "visited_hospitals": ["H2"], "ambulance_status": "in_transit"}, "action": {"hospital_id": "H2", "policy_score": 0.33704377286329346, "strategy": "balanced policy + guided-exploration + anti-stupidity guard"}, "outcome": {"status": "PARTIAL", "reason": "Condition worsened but remains temporarily transferable"}, "reward": 0.005000000000000032} {"seed": 202603, "task": "acde_hard", "difficulty": "hard", "step": 3, "state": {"patient_condition": "critical", "remaining_time_minutes": 12.0, "failed_hospitals": [], "visited_hospitals": ["H2", "H5"], "ambulance_status": "in_transit"}, "action": {"hospital_id": "H3", "policy_score": 0.27595701584132015, "strategy": "balanced policy + critical triage"}, "outcome": {"status": "REJECTED", "reason": "Hospital cannot admit: No specialist available, Hospital overloaded"}, "reward": 0.0} {"seed": 202603, "task": "acde_hard", "difficulty": "hard", "step": 4, "state": {"patient_condition": "critical", "remaining_time_minutes": 12.0, "failed_hospitals": ["H3"], "visited_hospitals": ["H2", "H5", "H3"], "ambulance_status": "rerouting"}, "action": {"hospital_id": "H6", "policy_score": 0.33264704163363146, "strategy": "risk-aware policy"}, "outcome": {"status": "REJECTED", "reason": "Hospital cannot admit: Hospital overloaded"}, "reward": 0.0} {"seed": 202701, "task": "acde_easy", "difficulty": "easy", "step": 1, "state": {"patient_condition": "serious", "remaining_time_minutes": 20.0, "failed_hospitals": [], "visited_hospitals": [], "ambulance_status": "en_route"}, "action": {"hospital_id": "H4", "policy_score": 0.38026864296379254, "strategy": "safe policy + guided-exploration + anti-stupidity guard"}, "outcome": {"status": "ACCEPTED", "reason": "Patient admitted and treatment began"}, "reward": 1.0} {"seed": 202702, "task": "acde_medium", "difficulty": "medium", "step": 1, "state": {"patient_condition": "serious", "remaining_time_minutes": 17.0, "failed_hospitals": [], "visited_hospitals": [], "ambulance_status": "en_route"}, "action": {"hospital_id": "H2", "policy_score": 0.42540812226350433, "strategy": "safe policy + anti-stupidity guard"}, "outcome": {"status": "PARTIAL", "reason": "Admitted with delays: doctor delayed"}, "reward": 0.4700000000000001} {"seed": 202702, "task": "acde_medium", "difficulty": "medium", "step": 2, "state": {"patient_condition": "serious", "remaining_time_minutes": 17.0, "failed_hospitals": [], "visited_hospitals": ["H2"], "ambulance_status": "in_transit"}, "action": {"hospital_id": "H2", "policy_score": 0.4288416047854854, "strategy": "balanced policy + anti-stupidity guard"}, "outcome": {"status": "REJECTED", "reason": "Hospital cannot admit: Hospital overloaded"}, "reward": 0.0} {"seed": 202702, "task": "acde_medium", "difficulty": "medium", "step": 3, "state": {"patient_condition": "serious", "remaining_time_minutes": 17.0, "failed_hospitals": ["H2"], "visited_hospitals": ["H2"], "ambulance_status": "rerouting"}, "action": {"hospital_id": "H1", "policy_score": 0.09306480283523665, "strategy": "risk-aware policy + guided-exploration + anti-stupidity guard"}, "outcome": {"status": "ACCEPTED", "reason": "Patient stabilized after delayed admission"}, "reward": 0.9280000000000002} {"seed": 202703, "task": "acde_hard", "difficulty": "hard", "step": 1, "state": {"patient_condition": "critical", "remaining_time_minutes": 12.0, "failed_hospitals": [], "visited_hospitals": [], "ambulance_status": "en_route"}, "action": {"hospital_id": "H6", "policy_score": 0.4785968513846229, "strategy": "safe policy + critical triage"}, "outcome": {"status": "REJECTED", "reason": "Hospital cannot admit: No specialist available"}, "reward": 0.0} {"seed": 202703, "task": "acde_hard", "difficulty": "hard", "step": 2, "state": {"patient_condition": "critical", "remaining_time_minutes": 12.0, "failed_hospitals": ["H2"], "visited_hospitals": ["H2"], "ambulance_status": "rerouting"}, "action": {"hospital_id": "H2", "policy_score": 0.08058556220342111, "strategy": "risk-aware policy + immediate-retry override"}, "outcome": {"status": "REJECTED", "reason": "Hidden mismatch at arrival (wrong risky guess). Rerouting required."}, "reward": 0.0} {"seed": 202703, "task": "acde_hard", "difficulty": "hard", "step": 3, "state": {"patient_condition": "critical", "remaining_time_minutes": 12.0, "failed_hospitals": ["H2"], "visited_hospitals": ["H2"], "ambulance_status": "rerouting"}, "action": {"hospital_id": "H6", "policy_score": 0.3216263383095567, "strategy": "risk-aware policy"}, "outcome": {"status": "REJECTED", "reason": "Hospital cannot admit: ICU unavailable, No specialist available"}, "reward": 0.04} {"seed": 202703, "task": "acde_hard", "difficulty": "hard", "step": 4, "state": {"patient_condition": "critical", "remaining_time_minutes": 12.0, "failed_hospitals": ["H2", "H5"], "visited_hospitals": ["H2", "H5"], "ambulance_status": "rerouting"}, "action": {"hospital_id": "H2", "policy_score": 0.11804437158103437, "strategy": "risk-aware policy + immediate-retry override"}, "outcome": {"status": "REJECTED", "reason": "Hospital cannot admit: Hospital overloaded"}, "reward": 0.0} {"seed": 202801, "task": "acde_easy", "difficulty": "easy", "step": 1, "state": {"patient_condition": "serious", "remaining_time_minutes": 20.0, "failed_hospitals": [], "visited_hospitals": [], "ambulance_status": "en_route"}, "action": {"hospital_id": "H1", "policy_score": 0.18037319218971745, "strategy": "safe policy"}, "outcome": {"status": "ACCEPTED", "reason": "Patient admitted and treatment began"}, "reward": 1.0} {"seed": 202802, "task": "acde_medium", "difficulty": "medium", "step": 1, "state": {"patient_condition": "critical", "remaining_time_minutes": 14.0, "failed_hospitals": [], "visited_hospitals": [], "ambulance_status": "en_route"}, "action": {"hospital_id": "H5", "policy_score": 0.3983094108606886, "strategy": "safe policy + critical triage"}, "outcome": {"status": "PARTIAL", "reason": "Critical deterioration managed temporarily; reroute still needed"}, "reward": 0.17500000000000002} {"seed": 202802, "task": "acde_medium", "difficulty": "medium", "step": 2, "state": {"patient_condition": "critical", "remaining_time_minutes": 14.0, "failed_hospitals": [], "visited_hospitals": ["H5"], "ambulance_status": "in_transit"}, "action": {"hospital_id": "H2", "policy_score": 0.3973426253330871, "strategy": "balanced policy + critical triage"}, "outcome": {"status": "REJECTED", "reason": "Condition became irreversible after delays"}, "reward": 0.11} {"seed": 202802, "task": "acde_medium", "difficulty": "medium", "step": 3, "state": {"patient_condition": "critical", "remaining_time_minutes": 14.0, "failed_hospitals": ["H2"], "visited_hospitals": ["H5", "H2"], "ambulance_status": "rerouting"}, "action": {"hospital_id": "H3", "policy_score": 0.4769015524657347, "strategy": "risk-aware policy"}, "outcome": {"status": "REJECTED", "reason": "Hospital cannot admit: No specialist available"}, "reward": 0.07} {"seed": 202802, "task": "acde_medium", "difficulty": "medium", "step": 4, "state": {"patient_condition": "critical", "remaining_time_minutes": 14.0, "failed_hospitals": ["H2", "H3"], "visited_hospitals": ["H5", "H2", "H3"], "ambulance_status": "rerouting"}, "action": {"hospital_id": "H5", "policy_score": 0.0722723116283798, "strategy": "risk-aware policy + anti-stupidity guard"}, "outcome": {"status": "REJECTED", "reason": "Hospital cannot admit: ICU unavailable"}, "reward": 0.0} {"seed": 202803, "task": "acde_hard", "difficulty": "hard", "step": 1, "state": {"patient_condition": "critical", "remaining_time_minutes": 11.0, "failed_hospitals": [], "visited_hospitals": [], "ambulance_status": "en_route"}, "action": {"hospital_id": "H1", "policy_score": 0.22391025757273347, "strategy": "safe policy + critical triage + guided-exploration"}, "outcome": {"status": "REJECTED", "reason": "Hospital cannot admit: ICU unavailable"}, "reward": 0.07} {"seed": 202803, "task": "acde_hard", "difficulty": "hard", "step": 2, "state": {"patient_condition": "critical", "remaining_time_minutes": 11.0, "failed_hospitals": ["H1"], "visited_hospitals": ["H1"], "ambulance_status": "rerouting"}, "action": {"hospital_id": "H3", "policy_score": 0.36595690254599844, "strategy": "risk-aware policy"}, "outcome": {"status": "PARTIAL", "reason": "Admitted with delays: prolonged transfer strain, patient worsened during transfer"}, "reward": 0.38750000000000007} {"seed": 202803, "task": "acde_hard", "difficulty": "hard", "step": 3, "state": {"patient_condition": "critical", "remaining_time_minutes": 11.0, "failed_hospitals": ["H1"], "visited_hospitals": ["H1", "H3"], "ambulance_status": "in_transit"}, "action": {"hospital_id": "H5", "policy_score": 0.39442075878892974, "strategy": "balanced policy + critical triage"}, "outcome": {"status": "REJECTED", "reason": "Condition became irreversible after delays"}, "reward": 0.14} {"seed": 202803, "task": "acde_hard", "difficulty": "hard", "step": 4, "state": {"patient_condition": "critical", "remaining_time_minutes": 11.0, "failed_hospitals": ["H1", "H5"], "visited_hospitals": ["H1", "H3", "H5"], "ambulance_status": "rerouting"}, "action": {"hospital_id": "H6", "policy_score": 0.3917102896175615, "strategy": "risk-aware policy + anti-stupidity guard"}, "outcome": {"status": "REJECTED", "reason": "Condition became irreversible after delays"}, "reward": 0.0} {"seed": 202901, "task": "acde_easy", "difficulty": "easy", "step": 1, "state": {"patient_condition": "serious", "remaining_time_minutes": 18.0, "failed_hospitals": [], "visited_hospitals": [], "ambulance_status": "en_route"}, "action": {"hospital_id": "H1", "policy_score": 0.31306762913030317, "strategy": "safe policy"}, "outcome": {"status": "ACCEPTED", "reason": "Patient stabilized after delayed admission"}, "reward": 0.8880000000000001} {"seed": 202902, "task": "acde_medium", "difficulty": "medium", "step": 1, "state": {"patient_condition": "critical", "remaining_time_minutes": 15.0, "failed_hospitals": [], "visited_hospitals": [], "ambulance_status": "en_route"}, "action": {"hospital_id": "H1", "policy_score": 0.36657097922350806, "strategy": "safe policy + critical triage"}, "outcome": {"status": "PARTIAL", "reason": "Early rejection mitigated by emergency field stabilization"}, "reward": 0.26500000000000007} {"seed": 202902, "task": "acde_medium", "difficulty": "medium", "step": 2, "state": {"patient_condition": "critical", "remaining_time_minutes": 15.0, "failed_hospitals": [], "visited_hospitals": ["H1"], "ambulance_status": "in_transit"}, "action": {"hospital_id": "H3", "policy_score": 0.4196605666263735, "strategy": "balanced policy + critical triage + anti-stupidity guard"}, "outcome": {"status": "PARTIAL", "reason": "Condition worsened but remains temporarily transferable"}, "reward": 0.17500000000000002} {"seed": 202902, "task": "acde_medium", "difficulty": "medium", "step": 3, "state": {"patient_condition": "unstable", "remaining_time_minutes": 15.0, "failed_hospitals": [], "visited_hospitals": ["H1", "H3"], "ambulance_status": "in_transit"}, "action": {"hospital_id": "H3", "policy_score": 0.3642622035488969, "strategy": "balanced policy + critical triage + anti-stupidity guard"}, "outcome": {"status": "ACCEPTED", "reason": "Patient stabilized after delayed admission"}, "reward": 0.7080000000000001} {"seed": 202903, "task": "acde_hard", "difficulty": "hard", "step": 1, "state": {"patient_condition": "critical", "remaining_time_minutes": 11.0, "failed_hospitals": [], "visited_hospitals": [], "ambulance_status": "en_route"}, "action": {"hospital_id": "H5", "policy_score": 0.3585055671729349, "strategy": "safe policy + critical triage + anti-stupidity guard"}, "outcome": {"status": "REJECTED", "reason": "Hospital cannot admit: ICU unavailable"}, "reward": 0.0} {"seed": 202903, "task": "acde_hard", "difficulty": "hard", "step": 2, "state": {"patient_condition": "critical", "remaining_time_minutes": 11.0, "failed_hospitals": ["H5"], "visited_hospitals": ["H5"], "ambulance_status": "rerouting"}, "action": {"hospital_id": "H6", "policy_score": 0.3972172279445488, "strategy": "risk-aware policy + anti-stupidity guard"}, "outcome": {"status": "PARTIAL", "reason": "Critical deterioration managed temporarily; reroute still needed"}, "reward": 0.155} {"seed": 202903, "task": "acde_hard", "difficulty": "hard", "step": 3, "state": {"patient_condition": "critical", "remaining_time_minutes": 11.0, "failed_hospitals": ["H5"], "visited_hospitals": ["H5", "H6"], "ambulance_status": "in_transit"}, "action": {"hospital_id": "H3", "policy_score": 0.2155659915203405, "strategy": "balanced policy + critical triage"}, "outcome": {"status": "REJECTED", "reason": "Condition became non-transferable during delay; immediate critical care failed"}, "reward": 0.0} {"seed": 203001, "task": "acde_easy", "difficulty": "easy", "step": 1, "state": {"patient_condition": "serious", "remaining_time_minutes": 20.0, "failed_hospitals": [], "visited_hospitals": [], "ambulance_status": "en_route"}, "action": {"hospital_id": "H3", "policy_score": 0.29934037995459517, "strategy": "safe policy"}, "outcome": {"status": "ACCEPTED", "reason": "Patient admitted and treatment began"}, "reward": 1.0} {"seed": 203002, "task": "acde_medium", "difficulty": "medium", "step": 1, "state": {"patient_condition": "serious", "remaining_time_minutes": 17.0, "failed_hospitals": [], "visited_hospitals": [], "ambulance_status": "en_route"}, "action": {"hospital_id": "H2", "policy_score": 0.30946896392387185, "strategy": "safe policy + anti-stupidity guard"}, "outcome": {"status": "PARTIAL", "reason": "Early rejection mitigated by emergency field stabilization"}, "reward": 0.275} {"seed": 203002, "task": "acde_medium", "difficulty": "medium", "step": 2, "state": {"patient_condition": "serious", "remaining_time_minutes": 17.0, "failed_hospitals": [], "visited_hospitals": ["H2"], "ambulance_status": "in_transit"}, "action": {"hospital_id": "H3", "policy_score": 0.3542020169013951, "strategy": "balanced policy + guided-exploration"}, "outcome": {"status": "ACCEPTED", "reason": "Condition stabilized after progressive treatment"}, "reward": 0.684} {"seed": 203003, "task": "acde_hard", "difficulty": "hard", "step": 1, "state": {"patient_condition": "critical", "remaining_time_minutes": 13.0, "failed_hospitals": [], "visited_hospitals": [], "ambulance_status": "en_route"}, "action": {"hospital_id": "H6", "policy_score": 0.4081241409187975, "strategy": "safe policy + critical triage + anti-stupidity guard"}, "outcome": {"status": "REJECTED", "reason": "Hidden mismatch at arrival (wrong risky guess). Rerouting required."}, "reward": 0.0} {"seed": 203003, "task": "acde_hard", "difficulty": "hard", "step": 2, "state": {"patient_condition": "critical", "remaining_time_minutes": 13.0, "failed_hospitals": ["H2"], "visited_hospitals": ["H2"], "ambulance_status": "rerouting"}, "action": {"hospital_id": "H5", "policy_score": 0.4583299937102532, "strategy": "risk-aware policy"}, "outcome": {"status": "REJECTED", "reason": "Hospital cannot admit: ICU unavailable"}, "reward": 0.0} {"seed": 203003, "task": "acde_hard", "difficulty": "hard", "step": 3, "state": {"patient_condition": "critical", "remaining_time_minutes": 13.0, "failed_hospitals": ["H2", "H5"], "visited_hospitals": ["H2", "H5"], "ambulance_status": "rerouting"}, "action": {"hospital_id": "H6", "policy_score": 0.4448762981257642, "strategy": "risk-aware policy"}, "outcome": {"status": "REJECTED", "reason": "Hidden mismatch at arrival (wrong risky guess). Rerouting required."}, "reward": 0.0} {"seed": 203003, "task": "acde_hard", "difficulty": "hard", "step": 4, "state": {"patient_condition": "critical", "remaining_time_minutes": 13.0, "failed_hospitals": ["H2", "H5", "H6"], "visited_hospitals": ["H2", "H5", "H6"], "ambulance_status": "rerouting"}, "action": {"hospital_id": "H4", "policy_score": 0.04168759041086244, "strategy": "risk-aware policy"}, "outcome": {"status": "REJECTED", "reason": "Hospital cannot admit: ICU unavailable, No specialist available"}, "reward": 0.0} {"seed": 203101, "task": "acde_easy", "difficulty": "easy", "step": 1, "state": {"patient_condition": "serious", "remaining_time_minutes": 18.0, "failed_hospitals": [], "visited_hospitals": [], "ambulance_status": "en_route"}, "action": {"hospital_id": "H1", "policy_score": 0.357923570076178, "strategy": "safe policy"}, "outcome": {"status": "ACCEPTED", "reason": "Patient stabilized after delayed admission"}, "reward": 0.8580000000000001} {"seed": 203102, "task": "acde_medium", "difficulty": "medium", "step": 1, "state": {"patient_condition": "critical", "remaining_time_minutes": 14.0, "failed_hospitals": [], "visited_hospitals": [], "ambulance_status": "en_route"}, "action": {"hospital_id": "H2", "policy_score": 0.4477036837666207, "strategy": "safe policy + critical triage"}, "outcome": {"status": "REJECTED", "reason": "Hospital cannot admit: ICU unavailable"}, "reward": 0.020000000000000018} {"seed": 203102, "task": "acde_medium", "difficulty": "medium", "step": 2, "state": {"patient_condition": "critical", "remaining_time_minutes": 14.0, "failed_hospitals": ["H5"], "visited_hospitals": ["H5"], "ambulance_status": "rerouting"}, "action": {"hospital_id": "H3", "policy_score": 0.09807325182694737, "strategy": "risk-aware policy + immediate-retry override"}, "outcome": {"status": "REJECTED", "reason": "Hospital cannot admit: ICU unavailable, Hospital overloaded"}, "reward": 0.11} {"seed": 203102, "task": "acde_medium", "difficulty": "medium", "step": 3, "state": {"patient_condition": "critical", "remaining_time_minutes": 14.0, "failed_hospitals": ["H5", "H2"], "visited_hospitals": ["H5", "H2"], "ambulance_status": "rerouting"}, "action": {"hospital_id": "H5", "policy_score": 0.0848690180801824, "strategy": "risk-aware policy + immediate-retry override"}, "outcome": {"status": "ACCEPTED", "reason": "Condition stabilized after progressive treatment"}, "reward": 0.48600000000000004} {"seed": 203103, "task": "acde_hard", "difficulty": "hard", "step": 1, "state": {"patient_condition": "critical", "remaining_time_minutes": 11.0, "failed_hospitals": [], "visited_hospitals": [], "ambulance_status": "en_route"}, "action": {"hospital_id": "H3", "policy_score": 0.38155543608915227, "strategy": "safe policy + critical triage + anti-stupidity guard"}, "outcome": {"status": "REJECTED", "reason": "Hospital cannot admit: ICU unavailable"}, "reward": 0.0} {"seed": 203103, "task": "acde_hard", "difficulty": "hard", "step": 2, "state": {"patient_condition": "critical", "remaining_time_minutes": 11.0, "failed_hospitals": ["H3"], "visited_hospitals": ["H3"], "ambulance_status": "rerouting"}, "action": {"hospital_id": "H5", "policy_score": 0.258125432689642, "strategy": "risk-aware policy + anti-stupidity guard"}, "outcome": {"status": "REJECTED", "reason": "Hospital cannot admit: ICU unavailable"}, "reward": 0.0} {"seed": 203103, "task": "acde_hard", "difficulty": "hard", "step": 3, "state": {"patient_condition": "critical", "remaining_time_minutes": 11.0, "failed_hospitals": ["H3", "H5"], "visited_hospitals": ["H3", "H5"], "ambulance_status": "rerouting"}, "action": {"hospital_id": "H1", "policy_score": 0.3870506843003317, "strategy": "risk-aware policy"}, "outcome": {"status": "REJECTED", "reason": "Hospital cannot admit: ICU unavailable"}, "reward": 0.0} {"seed": 203103, "task": "acde_hard", "difficulty": "hard", "step": 4, "state": {"patient_condition": "critical", "remaining_time_minutes": 11.0, "failed_hospitals": ["H3", "H5", "H6"], "visited_hospitals": ["H3", "H5", "H6"], "ambulance_status": "rerouting"}, "action": {"hospital_id": "H4", "policy_score": 0.08169091688740336, "strategy": "risk-aware policy + guided-exploration + immediate-retry override"}, "outcome": {"status": "REJECTED", "reason": "Hospital cannot admit: Hospital overloaded"}, "reward": 0.0} {"seed": 203201, "task": "acde_easy", "difficulty": "easy", "step": 1, "state": {"patient_condition": "serious", "remaining_time_minutes": 20.0, "failed_hospitals": [], "visited_hospitals": [], "ambulance_status": "en_route"}, "action": {"hospital_id": "H3", "policy_score": 0.22665702021719744, "strategy": "safe policy"}, "outcome": {"status": "ACCEPTED", "reason": "Patient stabilized after delayed admission"}, "reward": 0.8280000000000001} {"seed": 203202, "task": "acde_medium", "difficulty": "medium", "step": 1, "state": {"patient_condition": "serious", "remaining_time_minutes": 17.0, "failed_hospitals": [], "visited_hospitals": [], "ambulance_status": "en_route"}, "action": {"hospital_id": "H2", "policy_score": 0.29558448405953347, "strategy": "safe policy + guided-exploration"}, "outcome": {"status": "PARTIAL", "reason": "Early rejection mitigated by emergency field stabilization"}, "reward": 0.16500000000000004} {"seed": 203202, "task": "acde_medium", "difficulty": "medium", "step": 2, "state": {"patient_condition": "stable", "remaining_time_minutes": 17.0, "failed_hospitals": [], "visited_hospitals": ["H2"], "ambulance_status": "in_transit"}, "action": {"hospital_id": "H3", "policy_score": 0.3066678801166682, "strategy": "balanced policy"}, "outcome": {"status": "REJECTED", "reason": "Condition became irreversible after delays"}, "reward": 0.11} {"seed": 203202, "task": "acde_medium", "difficulty": "medium", "step": 3, "state": {"patient_condition": "stable", "remaining_time_minutes": 17.0, "failed_hospitals": ["H3"], "visited_hospitals": ["H2", "H3"], "ambulance_status": "rerouting"}, "action": {"hospital_id": "H2", "policy_score": 0.42213557086126485, "strategy": "risk-aware policy + anti-stupidity guard"}, "outcome": {"status": "REJECTED", "reason": "Condition relapsed after temporary stabilization"}, "reward": 0.0} {"seed": 203202, "task": "acde_medium", "difficulty": "medium", "step": 4, "state": {"patient_condition": "serious", "remaining_time_minutes": 17.0, "failed_hospitals": ["H3", "H5"], "visited_hospitals": ["H2", "H3", "H5"], "ambulance_status": "rerouting"}, "action": {"hospital_id": "H4", "policy_score": 0.07767030811137544, "strategy": "risk-aware policy + anti-stupidity guard + immediate-retry override"}, "outcome": {"status": "REJECTED", "reason": "Hospital cannot admit: No specialist available"}, "reward": 0.08} {"seed": 203203, "task": "acde_hard", "difficulty": "hard", "step": 1, "state": {"patient_condition": "critical", "remaining_time_minutes": 12.0, "failed_hospitals": [], "visited_hospitals": [], "ambulance_status": "en_route"}, "action": {"hospital_id": "H2", "policy_score": 0.3844541313788737, "strategy": "safe policy"}, "outcome": {"status": "REJECTED", "reason": "Hidden mismatch at arrival (wrong risky guess). Rerouting required."}, "reward": 0.0} {"seed": 203203, "task": "acde_hard", "difficulty": "hard", "step": 2, "state": {"patient_condition": "critical", "remaining_time_minutes": 12.0, "failed_hospitals": ["H2"], "visited_hospitals": ["H2"], "ambulance_status": "rerouting"}, "action": {"hospital_id": "H1", "policy_score": 0.09920087891504974, "strategy": "risk-aware policy + anti-stupidity guard"}, "outcome": {"status": "REJECTED", "reason": "Hospital cannot admit: No specialist available"}, "reward": 0.0} {"seed": 203203, "task": "acde_hard", "difficulty": "hard", "step": 3, "state": {"patient_condition": "critical", "remaining_time_minutes": 12.0, "failed_hospitals": ["H2", "H3"], "visited_hospitals": ["H2", "H3"], "ambulance_status": "rerouting"}, "action": {"hospital_id": "H2", "policy_score": 0.36829626751333566, "strategy": "risk-aware policy + immediate-retry override"}, "outcome": {"status": "REJECTED", "reason": "Hidden mismatch at arrival (wrong risky guess). Rerouting required."}, "reward": 0.0} {"seed": 203203, "task": "acde_hard", "difficulty": "hard", "step": 4, "state": {"patient_condition": "critical", "remaining_time_minutes": 12.0, "failed_hospitals": ["H2", "H3"], "visited_hospitals": ["H2", "H3"], "ambulance_status": "rerouting"}, "action": {"hospital_id": "H1", "policy_score": 0.10092689281520181, "strategy": "risk-aware policy"}, "outcome": {"status": "REJECTED", "reason": "Hospital cannot admit: Hospital overloaded"}, "reward": 0.009999999999999995} {"seed": 203301, "task": "acde_easy", "difficulty": "easy", "step": 1, "state": {"patient_condition": "critical", "remaining_time_minutes": 16.0, "failed_hospitals": [], "visited_hospitals": [], "ambulance_status": "en_route"}, "action": {"hospital_id": "H2", "policy_score": 0.48461481485522007, "strategy": "safe policy + critical triage"}, "outcome": {"status": "ACCEPTED", "reason": "Patient admitted and treatment began"}, "reward": 0.9500000000000001} {"seed": 203302, "task": "acde_medium", "difficulty": "medium", "step": 1, "state": {"patient_condition": "critical", "remaining_time_minutes": 15.0, "failed_hospitals": [], "visited_hospitals": [], "ambulance_status": "en_route"}, "action": {"hospital_id": "H1", "policy_score": 0.4281896707852887, "strategy": "safe policy + critical triage"}, "outcome": {"status": "PARTIAL", "reason": "Critical deterioration managed temporarily; reroute still needed"}, "reward": 0.17500000000000002} {"seed": 203302, "task": "acde_medium", "difficulty": "medium", "step": 2, "state": {"patient_condition": "critical", "remaining_time_minutes": 15.0, "failed_hospitals": [], "visited_hospitals": ["H1"], "ambulance_status": "in_transit"}, "action": {"hospital_id": "H5", "policy_score": 0.28188545629895256, "strategy": "balanced policy + critical triage + anti-stupidity guard"}, "outcome": {"status": "REJECTED", "reason": "Condition became irreversible after delays"}, "reward": 0.07} {"seed": 203302, "task": "acde_medium", "difficulty": "medium", "step": 3, "state": {"patient_condition": "critical", "remaining_time_minutes": 15.0, "failed_hospitals": ["H4"], "visited_hospitals": ["H1", "H4"], "ambulance_status": "rerouting"}, "action": {"hospital_id": "H3", "policy_score": 0.16670508325461983, "strategy": "risk-aware policy"}, "outcome": {"status": "REJECTED", "reason": "Hospital cannot admit: Hospital overloaded"}, "reward": 0.0} {"seed": 203302, "task": "acde_medium", "difficulty": "medium", "step": 4, "state": {"patient_condition": "critical", "remaining_time_minutes": 15.0, "failed_hospitals": ["H4", "H3"], "visited_hospitals": ["H1", "H4", "H3"], "ambulance_status": "rerouting"}, "action": {"hospital_id": "H5", "policy_score": 0.2601827884066416, "strategy": "risk-aware policy + anti-stupidity guard"}, "outcome": {"status": "REJECTED", "reason": "Condition relapsed after temporary stabilization"}, "reward": 0.07} {"seed": 203303, "task": "acde_hard", "difficulty": "hard", "step": 1, "state": {"patient_condition": "critical", "remaining_time_minutes": 12.0, "failed_hospitals": [], "visited_hospitals": [], "ambulance_status": "en_route"}, "action": {"hospital_id": "H3", "policy_score": 0.2920280085384916, "strategy": "safe policy + critical triage"}, "outcome": {"status": "PARTIAL", "reason": "Critical deterioration managed temporarily; reroute still needed"}, "reward": 0.26500000000000007} {"seed": 203303, "task": "acde_hard", "difficulty": "hard", "step": 2, "state": {"patient_condition": "critical", "remaining_time_minutes": 12.0, "failed_hospitals": [], "visited_hospitals": ["H3"], "ambulance_status": "in_transit"}, "action": {"hospital_id": "H5", "policy_score": 0.43536367409267823, "strategy": "balanced policy + critical triage"}, "outcome": {"status": "REJECTED", "reason": "Hospital cannot admit: ICU unavailable, No specialist available"}, "reward": 0.11} {"seed": 203303, "task": "acde_hard", "difficulty": "hard", "step": 3, "state": {"patient_condition": "critical", "remaining_time_minutes": 12.0, "failed_hospitals": ["H5"], "visited_hospitals": ["H3", "H5"], "ambulance_status": "rerouting"}, "action": {"hospital_id": "H3", "policy_score": 0.2519767287655702, "strategy": "risk-aware policy + anti-stupidity guard"}, "outcome": {"status": "REJECTED", "reason": "Hidden mismatch at arrival (wrong risky guess). Rerouting required."}, "reward": 0.0} {"seed": 203303, "task": "acde_hard", "difficulty": "hard", "step": 4, "state": {"patient_condition": "critical", "remaining_time_minutes": 12.0, "failed_hospitals": ["H5", "H3"], "visited_hospitals": ["H3", "H5"], "ambulance_status": "rerouting"}, "action": {"hospital_id": "H1", "policy_score": 0.05457914672345844, "strategy": "risk-aware policy + anti-stupidity guard"}, "outcome": {"status": "REJECTED", "reason": "Condition became irreversible after delays"}, "reward": 0.0} {"seed": 203401, "task": "acde_easy", "difficulty": "easy", "step": 1, "state": {"patient_condition": "critical", "remaining_time_minutes": 16.0, "failed_hospitals": [], "visited_hospitals": [], "ambulance_status": "en_route"}, "action": {"hospital_id": "H1", "policy_score": 0.46478426919853716, "strategy": "safe policy + critical triage"}, "outcome": {"status": "ACCEPTED", "reason": "Patient admitted and treatment began"}, "reward": 0.8500000000000001} {"seed": 203402, "task": "acde_medium", "difficulty": "medium", "step": 1, "state": {"patient_condition": "serious", "remaining_time_minutes": 17.0, "failed_hospitals": [], "visited_hospitals": [], "ambulance_status": "en_route"}, "action": {"hospital_id": "H2", "policy_score": 0.30923585765240613, "strategy": "safe policy + anti-stupidity guard"}, "outcome": {"status": "REJECTED", "reason": "Hospital cannot admit: ICU unavailable"}, "reward": 0.08} {"seed": 203402, "task": "acde_medium", "difficulty": "medium", "step": 2, "state": {"patient_condition": "serious", "remaining_time_minutes": 17.0, "failed_hospitals": ["H2"], "visited_hospitals": ["H2"], "ambulance_status": "rerouting"}, "action": {"hospital_id": "H3", "policy_score": 0.4189230992716588, "strategy": "risk-aware policy + anti-stupidity guard"}, "outcome": {"status": "PARTIAL", "reason": "Admitted with delays: prolonged transfer strain"}, "reward": 0.5100000000000001} {"seed": 203402, "task": "acde_medium", "difficulty": "medium", "step": 3, "state": {"patient_condition": "serious", "remaining_time_minutes": 17.0, "failed_hospitals": ["H2"], "visited_hospitals": ["H2", "H3"], "ambulance_status": "in_transit"}, "action": {"hospital_id": "H3", "policy_score": 0.43546975770655516, "strategy": "balanced policy + anti-stupidity guard"}, "outcome": {"status": "REJECTED", "reason": "Condition became non-transferable during delay; immediate critical care failed"}, "reward": 0.0} {"seed": 203403, "task": "acde_hard", "difficulty": "hard", "step": 1, "state": {"patient_condition": "critical", "remaining_time_minutes": 11.0, "failed_hospitals": [], "visited_hospitals": [], "ambulance_status": "en_route"}, "action": {"hospital_id": "H1", "policy_score": 0.3681391739524484, "strategy": "safe policy + critical triage"}, "outcome": {"status": "REJECTED", "reason": "Hospital cannot admit: ICU unavailable, No specialist available"}, "reward": 0.1} {"seed": 203403, "task": "acde_hard", "difficulty": "hard", "step": 2, "state": {"patient_condition": "critical", "remaining_time_minutes": 11.0, "failed_hospitals": ["H1"], "visited_hospitals": ["H1"], "ambulance_status": "rerouting"}, "action": {"hospital_id": "H3", "policy_score": 0.37837945296193765, "strategy": "risk-aware policy"}, "outcome": {"status": "REJECTED", "reason": "Emergency beds became unavailable during arrival"}, "reward": 0.0} {"seed": 203403, "task": "acde_hard", "difficulty": "hard", "step": 3, "state": {"patient_condition": "critical", "remaining_time_minutes": 11.0, "failed_hospitals": ["H1", "H3"], "visited_hospitals": ["H1", "H3"], "ambulance_status": "rerouting"}, "action": {"hospital_id": "H5", "policy_score": 0.35108995655768566, "strategy": "risk-aware policy"}, "outcome": {"status": "REJECTED", "reason": "Hidden mismatch at arrival (wrong risky guess). Rerouting required."}, "reward": 0.0} {"seed": 203403, "task": "acde_hard", "difficulty": "hard", "step": 4, "state": {"patient_condition": "critical", "remaining_time_minutes": 11.0, "failed_hospitals": ["H1", "H3", "H5"], "visited_hospitals": ["H1", "H3", "H5"], "ambulance_status": "rerouting"}, "action": {"hospital_id": "H6", "policy_score": 0.05561222216001024, "strategy": "risk-aware policy"}, "outcome": {"status": "REJECTED", "reason": "Condition relapsed after temporary stabilization"}, "reward": 0.14} {"seed": 203501, "task": "acde_easy", "difficulty": "easy", "step": 1, "state": {"patient_condition": "critical", "remaining_time_minutes": 16.0, "failed_hospitals": [], "visited_hospitals": [], "ambulance_status": "en_route"}, "action": {"hospital_id": "H2", "policy_score": 0.4048713742500039, "strategy": "safe policy + critical triage + guided-exploration"}, "outcome": {"status": "PARTIAL", "reason": "Early rejection mitigated by emergency field stabilization"}, "reward": 0.335} {"seed": 203501, "task": "acde_easy", "difficulty": "easy", "step": 2, "state": {"patient_condition": "critical", "remaining_time_minutes": 16.0, "failed_hospitals": [], "visited_hospitals": ["H2"], "ambulance_status": "in_transit"}, "action": {"hospital_id": "H1", "policy_score": 0.34123844525582936, "strategy": "balanced policy + critical triage"}, "outcome": {"status": "ACCEPTED", "reason": "Patient admitted and treatment began"}, "reward": 0.98} {"seed": 203502, "task": "acde_medium", "difficulty": "medium", "step": 1, "state": {"patient_condition": "serious", "remaining_time_minutes": 17.0, "failed_hospitals": [], "visited_hospitals": [], "ambulance_status": "en_route"}, "action": {"hospital_id": "H5", "policy_score": 0.2545975973522379, "strategy": "safe policy"}, "outcome": {"status": "PARTIAL", "reason": "Early rejection mitigated by emergency field stabilization"}, "reward": 0.16500000000000004} {"seed": 203502, "task": "acde_medium", "difficulty": "medium", "step": 2, "state": {"patient_condition": "serious", "remaining_time_minutes": 17.0, "failed_hospitals": [], "visited_hospitals": ["H5"], "ambulance_status": "in_transit"}, "action": {"hospital_id": "H3", "policy_score": 0.29435462739340534, "strategy": "balanced policy"}, "outcome": {"status": "PARTIAL", "reason": "Condition worsened but remains temporarily transferable"}, "reward": 0.275} {"seed": 203502, "task": "acde_medium", "difficulty": "medium", "step": 3, "state": {"patient_condition": "stable", "remaining_time_minutes": 17.0, "failed_hospitals": [], "visited_hospitals": ["H5", "H3"], "ambulance_status": "in_transit"}, "action": {"hospital_id": "H5", "policy_score": 0.3348023936284714, "strategy": "balanced policy + anti-stupidity guard"}, "outcome": {"status": "REJECTED", "reason": "Condition became irreversible after delays"}, "reward": 0.0} {"seed": 203502, "task": "acde_medium", "difficulty": "medium", "step": 4, "state": {"patient_condition": "serious", "remaining_time_minutes": 17.0, "failed_hospitals": ["H5"], "visited_hospitals": ["H5", "H3"], "ambulance_status": "rerouting"}, "action": {"hospital_id": "H3", "policy_score": 0.3287393562734675, "strategy": "risk-aware policy + anti-stupidity guard"}, "outcome": {"status": "ACCEPTED", "reason": "Patient stabilized after critical delay"}, "reward": 0.5156000000000001} {"seed": 203503, "task": "acde_hard", "difficulty": "hard", "step": 1, "state": {"patient_condition": "critical", "remaining_time_minutes": 11.0, "failed_hospitals": [], "visited_hospitals": [], "ambulance_status": "en_route"}, "action": {"hospital_id": "H3", "policy_score": 0.393372784520385, "strategy": "safe policy + critical triage"}, "outcome": {"status": "REJECTED", "reason": "Hidden mismatch at arrival (wrong risky guess). Rerouting required."}, "reward": 0.0} {"seed": 203503, "task": "acde_hard", "difficulty": "hard", "step": 2, "state": {"patient_condition": "critical", "remaining_time_minutes": 11.0, "failed_hospitals": ["H1"], "visited_hospitals": ["H1"], "ambulance_status": "rerouting"}, "action": {"hospital_id": "H6", "policy_score": 0.27429437383515265, "strategy": "risk-aware policy"}, "outcome": {"status": "REJECTED", "reason": "Hospital cannot admit: ICU unavailable, No specialist available"}, "reward": 0.11} {"seed": 203503, "task": "acde_hard", "difficulty": "hard", "step": 3, "state": {"patient_condition": "critical", "remaining_time_minutes": 11.0, "failed_hospitals": ["H1", "H6"], "visited_hospitals": ["H1", "H6"], "ambulance_status": "rerouting"}, "action": {"hospital_id": "H5", "policy_score": 0.35945785161905247, "strategy": "risk-aware policy"}, "outcome": {"status": "PARTIAL", "reason": "Admitted with delays: prolonged transfer strain, patient worsened during transfer"}, "reward": 0.35750000000000004} {"seed": 203503, "task": "acde_hard", "difficulty": "hard", "step": 4, "state": {"patient_condition": "unstable", "remaining_time_minutes": 11.0, "failed_hospitals": ["H1", "H6"], "visited_hospitals": ["H1", "H6", "H5"], "ambulance_status": "in_transit"}, "action": {"hospital_id": "H5", "policy_score": 0.4182135940523963, "strategy": "balanced policy + anti-stupidity guard"}, "outcome": {"status": "REJECTED", "reason": "ICU got full moments before handover"}, "reward": 0.0} {"seed": 555, "task": "acde_easy", "difficulty": "easy", "step": 1, "state": {"patient_condition": "critical", "remaining_time_minutes": 16.0, "failed_hospitals": [], "visited_hospitals": [], "ambulance_status": "en_route"}, "action": {"hospital_id": "H1", "policy_score": 0.254727802499404, "strategy": "safe policy + critical triage"}, "outcome": {"status": "ACCEPTED", "reason": "Patient admitted and treatment began"}, "reward": 0.94} {"seed": 556, "task": "acde_medium", "difficulty": "medium", "step": 1, "state": {"patient_condition": "critical", "remaining_time_minutes": 15.0, "failed_hospitals": [], "visited_hospitals": [], "ambulance_status": "en_route"}, "action": {"hospital_id": "H5", "policy_score": 0.4061660862547171, "strategy": "safe policy + critical triage + anti-stupidity guard"}, "outcome": {"status": "PARTIAL", "reason": "Initial triage completed; transfer monitoring still required"}, "reward": 0.281} {"seed": 556, "task": "acde_medium", "difficulty": "medium", "step": 2, "state": {"patient_condition": "critical", "remaining_time_minutes": 15.0, "failed_hospitals": [], "visited_hospitals": ["H5"], "ambulance_status": "in_transit"}, "action": {"hospital_id": "H1", "policy_score": 0.4337871301921077, "strategy": "balanced policy + critical triage"}, "outcome": {"status": "REJECTED", "reason": "Hospital cannot admit: Hospital overloaded"}, "reward": 0.009999999999999995} {"seed": 556, "task": "acde_medium", "difficulty": "medium", "step": 3, "state": {"patient_condition": "critical", "remaining_time_minutes": 15.0, "failed_hospitals": ["H1"], "visited_hospitals": ["H5", "H1"], "ambulance_status": "rerouting"}, "action": {"hospital_id": "H5", "policy_score": 0.35840780736483824, "strategy": "risk-aware policy + anti-stupidity guard"}, "outcome": {"status": "REJECTED", "reason": "Condition became irreversible after delays"}, "reward": 0.0} {"seed": 556, "task": "acde_medium", "difficulty": "medium", "step": 4, "state": {"patient_condition": "critical", "remaining_time_minutes": 15.0, "failed_hospitals": ["H1", "H5"], "visited_hospitals": ["H5", "H1"], "ambulance_status": "rerouting"}, "action": {"hospital_id": "H3", "policy_score": 0.07414865607113472, "strategy": "risk-aware policy"}, "outcome": {"status": "ACCEPTED", "reason": "Patient stabilized after critical delay"}, "reward": 0.4456000000000001} {"seed": 557, "task": "acde_hard", "difficulty": "hard", "step": 1, "state": {"patient_condition": "critical", "remaining_time_minutes": 12.0, "failed_hospitals": [], "visited_hospitals": [], "ambulance_status": "en_route"}, "action": {"hospital_id": "H5", "policy_score": 0.4621819243258249, "strategy": "safe policy + guided-exploration"}, "outcome": {"status": "REJECTED", "reason": "Hidden mismatch at arrival (wrong risky guess). Rerouting required."}, "reward": 0.0} {"seed": 557, "task": "acde_hard", "difficulty": "hard", "step": 2, "state": {"patient_condition": "critical", "remaining_time_minutes": 12.0, "failed_hospitals": ["H5"], "visited_hospitals": ["H5"], "ambulance_status": "rerouting"}, "action": {"hospital_id": "H2", "policy_score": 0.46993294540326186, "strategy": "risk-aware policy"}, "outcome": {"status": "ACCEPTED", "reason": "Condition stabilized after progressive treatment"}, "reward": 0.5840000000000001} {"seed": 655, "task": "acde_easy", "difficulty": "easy", "step": 1, "state": {"patient_condition": "critical", "remaining_time_minutes": 16.0, "failed_hospitals": [], "visited_hospitals": [], "ambulance_status": "en_route"}, "action": {"hospital_id": "H2", "policy_score": 0.4830691389753652, "strategy": "safe policy + critical triage"}, "outcome": {"status": "ACCEPTED", "reason": "Patient admitted and treatment began"}, "reward": 0.91} {"seed": 656, "task": "acde_medium", "difficulty": "medium", "step": 1, "state": {"patient_condition": "critical", "remaining_time_minutes": 15.0, "failed_hospitals": [], "visited_hospitals": [], "ambulance_status": "en_route"}, "action": {"hospital_id": "H1", "policy_score": 0.43393060669282485, "strategy": "safe policy + critical triage + anti-stupidity guard"}, "outcome": {"status": "ACCEPTED", "reason": "Patient admitted and treatment began"}, "reward": 0.98} {"seed": 657, "task": "acde_hard", "difficulty": "hard", "step": 1, "state": {"patient_condition": "critical", "remaining_time_minutes": 13.0, "failed_hospitals": [], "visited_hospitals": [], "ambulance_status": "en_route"}, "action": {"hospital_id": "H6", "policy_score": 0.4777184544239215, "strategy": "safe policy + critical triage"}, "outcome": {"status": "REJECTED", "reason": "Hospital cannot admit: Hospital overloaded"}, "reward": 0.07} {"seed": 657, "task": "acde_hard", "difficulty": "hard", "step": 2, "state": {"patient_condition": "critical", "remaining_time_minutes": 13.0, "failed_hospitals": ["H6"], "visited_hospitals": ["H6"], "ambulance_status": "rerouting"}, "action": {"hospital_id": "H2", "policy_score": 0.06587365834612231, "strategy": "risk-aware policy"}, "outcome": {"status": "REJECTED", "reason": "Hidden mismatch at arrival (wrong risky guess). Rerouting required."}, "reward": 0.0} {"seed": 657, "task": "acde_hard", "difficulty": "hard", "step": 3, "state": {"patient_condition": "critical", "remaining_time_minutes": 13.0, "failed_hospitals": ["H6", "H1"], "visited_hospitals": ["H6", "H1"], "ambulance_status": "rerouting"}, "action": {"hospital_id": "H6", "policy_score": 0.4171668892918258, "strategy": "risk-aware policy + immediate-retry override"}, "outcome": {"status": "PARTIAL", "reason": "Critical deterioration managed temporarily; reroute still needed"}, "reward": 0.0} {"seed": 657, "task": "acde_hard", "difficulty": "hard", "step": 4, "state": {"patient_condition": "critical", "remaining_time_minutes": 13.0, "failed_hospitals": ["H6", "H1"], "visited_hospitals": ["H6", "H1"], "ambulance_status": "in_transit"}, "action": {"hospital_id": "H2", "policy_score": 0.15798456158167448, "strategy": "balanced policy"}, "outcome": {"status": "REJECTED", "reason": "Hospital cannot admit: No specialist available"}, "reward": 0.0} {"seed": 755, "task": "acde_easy", "difficulty": "easy", "step": 1, "state": {"patient_condition": "serious", "remaining_time_minutes": 18.0, "failed_hospitals": [], "visited_hospitals": [], "ambulance_status": "en_route"}, "action": {"hospital_id": "H1", "policy_score": 0.26036150247379014, "strategy": "safe policy"}, "outcome": {"status": "ACCEPTED", "reason": "Patient admitted and treatment began"}, "reward": 1.0} {"seed": 756, "task": "acde_medium", "difficulty": "medium", "step": 1, "state": {"patient_condition": "serious", "remaining_time_minutes": 17.0, "failed_hospitals": [], "visited_hospitals": [], "ambulance_status": "en_route"}, "action": {"hospital_id": "H2", "policy_score": 0.33013809809780814, "strategy": "safe policy"}, "outcome": {"status": "REJECTED", "reason": "Hidden mismatch at arrival (wrong risky guess). Rerouting required."}, "reward": 0.0} {"seed": 756, "task": "acde_medium", "difficulty": "medium", "step": 2, "state": {"patient_condition": "serious", "remaining_time_minutes": 17.0, "failed_hospitals": ["H2"], "visited_hospitals": ["H2"], "ambulance_status": "rerouting"}, "action": {"hospital_id": "H3", "policy_score": 0.4251531824630478, "strategy": "risk-aware policy"}, "outcome": {"status": "PARTIAL", "reason": "Critical deterioration managed temporarily; reroute still needed"}, "reward": 0.315} {"seed": 756, "task": "acde_medium", "difficulty": "medium", "step": 3, "state": {"patient_condition": "stable", "remaining_time_minutes": 17.0, "failed_hospitals": ["H2"], "visited_hospitals": ["H2", "H3"], "ambulance_status": "in_transit"}, "action": {"hospital_id": "H4", "policy_score": 0.07234411365253952, "strategy": "balanced policy + guided-exploration"}, "outcome": {"status": "ACCEPTED", "reason": "Patient stabilized after delayed admission"}, "reward": 0.8980000000000001} {"seed": 757, "task": "acde_hard", "difficulty": "hard", "step": 1, "state": {"patient_condition": "critical", "remaining_time_minutes": 13.0, "failed_hospitals": [], "visited_hospitals": [], "ambulance_status": "en_route"}, "action": {"hospital_id": "H2", "policy_score": 0.49962276007921047, "strategy": "safe policy"}, "outcome": {"status": "PARTIAL", "reason": "Admitted with delays: prolonged transfer strain, hospital busy but manageable"}, "reward": 0.31750000000000006} {"seed": 757, "task": "acde_hard", "difficulty": "hard", "step": 2, "state": {"patient_condition": "critical", "remaining_time_minutes": 13.0, "failed_hospitals": [], "visited_hospitals": ["H5"], "ambulance_status": "in_transit"}, "action": {"hospital_id": "H2", "policy_score": 0.49955485852189263, "strategy": "balanced policy"}, "outcome": {"status": "REJECTED", "reason": "Hospital cannot admit: ICU unavailable, No specialist available"}, "reward": 0.0} {"seed": 757, "task": "acde_hard", "difficulty": "hard", "step": 3, "state": {"patient_condition": "critical", "remaining_time_minutes": 13.0, "failed_hospitals": ["H2"], "visited_hospitals": ["H5", "H2"], "ambulance_status": "rerouting"}, "action": {"hospital_id": "H3", "policy_score": 0.16440008228758887, "strategy": "risk-aware policy"}, "outcome": {"status": "ACCEPTED", "reason": "Patient stabilized after critical delay"}, "reward": 0.6556000000000001} {"seed": 855, "task": "acde_easy", "difficulty": "easy", "step": 1, "state": {"patient_condition": "critical", "remaining_time_minutes": 16.0, "failed_hospitals": [], "visited_hospitals": [], "ambulance_status": "en_route"}, "action": {"hospital_id": "H1", "policy_score": 0.4884154826857476, "strategy": "safe policy + critical triage"}, "outcome": {"status": "ACCEPTED", "reason": "Patient admitted and treatment began"}, "reward": 0.8500000000000001} {"seed": 856, "task": "acde_medium", "difficulty": "medium", "step": 1, "state": {"patient_condition": "serious", "remaining_time_minutes": 17.0, "failed_hospitals": [], "visited_hospitals": [], "ambulance_status": "en_route"}, "action": {"hospital_id": "H2", "policy_score": 0.37629505306621236, "strategy": "safe policy + anti-stupidity guard"}, "outcome": {"status": "REJECTED", "reason": "Condition became non-transferable during delay; immediate critical care failed"}, "reward": 0.08} {"seed": 857, "task": "acde_hard", "difficulty": "hard", "step": 1, "state": {"patient_condition": "critical", "remaining_time_minutes": 13.0, "failed_hospitals": [], "visited_hospitals": [], "ambulance_status": "en_route"}, "action": {"hospital_id": "H2", "policy_score": 0.32785097895319304, "strategy": "safe policy + critical triage"}, "outcome": {"status": "REJECTED", "reason": "Condition became non-transferable during delay; immediate critical care failed"}, "reward": 0.04} {"seed": 955, "task": "acde_easy", "difficulty": "easy", "step": 1, "state": {"patient_condition": "critical", "remaining_time_minutes": 16.0, "failed_hospitals": [], "visited_hospitals": [], "ambulance_status": "en_route"}, "action": {"hospital_id": "H2", "policy_score": 0.4023376850704094, "strategy": "safe policy + critical triage"}, "outcome": {"status": "PARTIAL", "reason": "Admitted with delays: prolonged transfer strain, hospital busy but manageable"}, "reward": 0.25750000000000006} {"seed": 955, "task": "acde_easy", "difficulty": "easy", "step": 2, "state": {"patient_condition": "critical", "remaining_time_minutes": 16.0, "failed_hospitals": [], "visited_hospitals": ["H2"], "ambulance_status": "in_transit"}, "action": {"hospital_id": "H1", "policy_score": 0.46217880471004785, "strategy": "balanced policy + critical triage"}, "outcome": {"status": "REJECTED", "reason": "Condition became non-transferable during delay; immediate critical care failed"}, "reward": 0.009999999999999995} {"seed": 956, "task": "acde_medium", "difficulty": "medium", "step": 1, "state": {"patient_condition": "critical", "remaining_time_minutes": 15.0, "failed_hospitals": [], "visited_hospitals": [], "ambulance_status": "en_route"}, "action": {"hospital_id": "H4", "policy_score": 0.32761786539914983, "strategy": "safe policy"}, "outcome": {"status": "PARTIAL", "reason": "Critical deterioration managed temporarily; reroute still needed"}, "reward": 0.21500000000000002} {"seed": 956, "task": "acde_medium", "difficulty": "medium", "step": 2, "state": {"patient_condition": "critical", "remaining_time_minutes": 15.0, "failed_hospitals": [], "visited_hospitals": ["H4"], "ambulance_status": "in_transit"}, "action": {"hospital_id": "H5", "policy_score": 0.394930649253581, "strategy": "balanced policy + critical triage"}, "outcome": {"status": "ACCEPTED", "reason": "Patient stabilized after critical delay"}, "reward": 0.5656000000000001} {"seed": 957, "task": "acde_hard", "difficulty": "hard", "step": 1, "state": {"patient_condition": "critical", "remaining_time_minutes": 11.0, "failed_hospitals": [], "visited_hospitals": [], "ambulance_status": "en_route"}, "action": {"hospital_id": "H5", "policy_score": 0.42565717861726177, "strategy": "safe policy + critical triage + anti-stupidity guard"}, "outcome": {"status": "PARTIAL", "reason": "Admitted with delays: prolonged transfer strain"}, "reward": 0.3400000000000001} {"seed": 957, "task": "acde_hard", "difficulty": "hard", "step": 2, "state": {"patient_condition": "unstable", "remaining_time_minutes": 11.0, "failed_hospitals": [], "visited_hospitals": ["H5"], "ambulance_status": "in_transit"}, "action": {"hospital_id": "H6", "policy_score": 0.21108583467028172, "strategy": "balanced policy"}, "outcome": {"status": "REJECTED", "reason": "Hidden mismatch at arrival (wrong risky guess). Rerouting required."}, "reward": 0.0} {"seed": 957, "task": "acde_hard", "difficulty": "hard", "step": 3, "state": {"patient_condition": "unstable", "remaining_time_minutes": 11.0, "failed_hospitals": ["H6"], "visited_hospitals": ["H5", "H6"], "ambulance_status": "rerouting"}, "action": {"hospital_id": "H4", "policy_score": 0.2722935143329109, "strategy": "risk-aware policy + anti-stupidity guard"}, "outcome": {"status": "REJECTED", "reason": "Hospital cannot admit: No specialist available"}, "reward": 0.04} {"seed": 957, "task": "acde_hard", "difficulty": "hard", "step": 4, "state": {"patient_condition": "unstable", "remaining_time_minutes": 11.0, "failed_hospitals": ["H6", "H4"], "visited_hospitals": ["H5", "H6", "H4"], "ambulance_status": "rerouting"}, "action": {"hospital_id": "H3", "policy_score": 0.41861212567626427, "strategy": "risk-aware policy + guided-exploration"}, "outcome": {"status": "REJECTED", "reason": "Hospital cannot admit: Hospital overloaded"}, "reward": 0.11} {"seed": 1055, "task": "acde_easy", "difficulty": "easy", "step": 1, "state": {"patient_condition": "critical", "remaining_time_minutes": 16.0, "failed_hospitals": [], "visited_hospitals": [], "ambulance_status": "en_route"}, "action": {"hospital_id": "H1", "policy_score": 0.4946520808120031, "strategy": "safe policy + critical triage"}, "outcome": {"status": "REJECTED", "reason": "Hospital cannot admit: No specialist available"}, "reward": 0.1} {"seed": 1055, "task": "acde_easy", "difficulty": "easy", "step": 2, "state": {"patient_condition": "critical", "remaining_time_minutes": 16.0, "failed_hospitals": ["H1"], "visited_hospitals": ["H1"], "ambulance_status": "rerouting"}, "action": {"hospital_id": "H2", "policy_score": 0.46705274420705745, "strategy": "risk-aware policy"}, "outcome": {"status": "REJECTED", "reason": "Hidden mismatch at arrival (wrong risky guess). Rerouting required."}, "reward": 0.0} {"seed": 1055, "task": "acde_easy", "difficulty": "easy", "step": 3, "state": {"patient_condition": "critical", "remaining_time_minutes": 16.0, "failed_hospitals": ["H1", "H2"], "visited_hospitals": ["H1", "H2"], "ambulance_status": "rerouting"}, "action": {"hospital_id": "H3", "policy_score": 0.021072925227370396, "strategy": "risk-aware policy + guided-exploration"}, "outcome": {"status": "ACCEPTED", "reason": "Emergency stabilization at last attempt"}, "reward": 0.7844} {"seed": 1056, "task": "acde_medium", "difficulty": "medium", "step": 1, "state": {"patient_condition": "serious", "remaining_time_minutes": 17.0, "failed_hospitals": [], "visited_hospitals": [], "ambulance_status": "en_route"}, "action": {"hospital_id": "H5", "policy_score": 0.2404465572596958, "strategy": "safe policy + guided-exploration"}, "outcome": {"status": "PARTIAL", "reason": "Initial triage completed; transfer monitoring still required"}, "reward": 0.371} {"seed": 1056, "task": "acde_medium", "difficulty": "medium", "step": 2, "state": {"patient_condition": "serious", "remaining_time_minutes": 17.0, "failed_hospitals": [], "visited_hospitals": ["H2"], "ambulance_status": "in_transit"}, "action": {"hospital_id": "H3", "policy_score": 0.3032125367693344, "strategy": "balanced policy"}, "outcome": {"status": "REJECTED", "reason": "Condition became irreversible after delays"}, "reward": 0.11} {"seed": 1056, "task": "acde_medium", "difficulty": "medium", "step": 3, "state": {"patient_condition": "serious", "remaining_time_minutes": 17.0, "failed_hospitals": ["H3"], "visited_hospitals": ["H2", "H3"], "ambulance_status": "rerouting"}, "action": {"hospital_id": "H5", "policy_score": 0.31819517199163627, "strategy": "risk-aware policy + anti-stupidity guard"}, "outcome": {"status": "REJECTED", "reason": "Hidden mismatch at arrival (wrong risky guess). Rerouting required."}, "reward": 0.0} {"seed": 1056, "task": "acde_medium", "difficulty": "medium", "step": 4, "state": {"patient_condition": "serious", "remaining_time_minutes": 17.0, "failed_hospitals": ["H3", "H5"], "visited_hospitals": ["H2", "H3", "H5"], "ambulance_status": "rerouting"}, "action": {"hospital_id": "H2", "policy_score": 0.45336346649822323, "strategy": "risk-aware policy + anti-stupidity guard"}, "outcome": {"status": "ACCEPTED", "reason": "Patient stabilized after critical delay"}, "reward": 0.5156000000000001} {"seed": 1057, "task": "acde_hard", "difficulty": "hard", "step": 1, "state": {"patient_condition": "critical", "remaining_time_minutes": 11.0, "failed_hospitals": [], "visited_hospitals": [], "ambulance_status": "en_route"}, "action": {"hospital_id": "H5", "policy_score": 0.4202833343707889, "strategy": "safe policy + critical triage"}, "outcome": {"status": "PARTIAL", "reason": "Admitted with delays: prolonged transfer strain"}, "reward": 0.3400000000000001} {"seed": 1057, "task": "acde_hard", "difficulty": "hard", "step": 2, "state": {"patient_condition": "critical", "remaining_time_minutes": 11.0, "failed_hospitals": [], "visited_hospitals": ["H5"], "ambulance_status": "in_transit"}, "action": {"hospital_id": "H3", "policy_score": 0.4054161391534861, "strategy": "balanced policy + critical triage + anti-stupidity guard"}, "outcome": {"status": "REJECTED", "reason": "Hidden mismatch at arrival (wrong risky guess). Rerouting required."}, "reward": 0.0} {"seed": 1057, "task": "acde_hard", "difficulty": "hard", "step": 3, "state": {"patient_condition": "critical", "remaining_time_minutes": 11.0, "failed_hospitals": ["H3"], "visited_hospitals": ["H5", "H3"], "ambulance_status": "rerouting"}, "action": {"hospital_id": "H1", "policy_score": 0.399076216033822, "strategy": "risk-aware policy + anti-stupidity guard"}, "outcome": {"status": "REJECTED", "reason": "Hospital cannot admit: No specialist available"}, "reward": 0.0} {"seed": 1057, "task": "acde_hard", "difficulty": "hard", "step": 4, "state": {"patient_condition": "critical", "remaining_time_minutes": 11.0, "failed_hospitals": ["H3", "H4"], "visited_hospitals": ["H5", "H3", "H4"], "ambulance_status": "rerouting"}, "action": {"hospital_id": "H5", "policy_score": 0.17586863412116815, "strategy": "risk-aware policy + immediate-retry override"}, "outcome": {"status": "REJECTED", "reason": "Hospital cannot admit: ICU unavailable, Hospital overloaded"}, "reward": 0.0} {"seed": 1155, "task": "acde_easy", "difficulty": "easy", "step": 1, "state": {"patient_condition": "serious", "remaining_time_minutes": 20.0, "failed_hospitals": [], "visited_hospitals": [], "ambulance_status": "en_route"}, "action": {"hospital_id": "H1", "policy_score": 0.3807041619103531, "strategy": "safe policy + anti-stupidity guard"}, "outcome": {"status": "REJECTED", "reason": "Hospital cannot admit: No specialist available"}, "reward": 0.14} {"seed": 1155, "task": "acde_easy", "difficulty": "easy", "step": 2, "state": {"patient_condition": "serious", "remaining_time_minutes": 20.0, "failed_hospitals": ["H1"], "visited_hospitals": ["H1"], "ambulance_status": "rerouting"}, "action": {"hospital_id": "H3", "policy_score": 0.4501660351870285, "strategy": "risk-aware policy"}, "outcome": {"status": "REJECTED", "reason": "Critical treatment machine failed at admission"}, "reward": 0.0} {"seed": 1155, "task": "acde_easy", "difficulty": "easy", "step": 3, "state": {"patient_condition": "unstable", "remaining_time_minutes": 20.0, "failed_hospitals": ["H1", "H3"], "visited_hospitals": ["H1", "H3"], "ambulance_status": "rerouting"}, "action": {"hospital_id": "H2", "policy_score": 0.06885619384641059, "strategy": "risk-aware policy + anti-stupidity guard"}, "outcome": {"status": "ACCEPTED", "reason": "Patient stabilized after delayed admission"}, "reward": 0.8580000000000001} {"seed": 1156, "task": "acde_medium", "difficulty": "medium", "step": 1, "state": {"patient_condition": "serious", "remaining_time_minutes": 17.0, "failed_hospitals": [], "visited_hospitals": [], "ambulance_status": "en_route"}, "action": {"hospital_id": "H2", "policy_score": 0.25008051017311134, "strategy": "safe policy"}, "outcome": {"status": "REJECTED", "reason": "Hidden mismatch at arrival (wrong risky guess). Rerouting required."}, "reward": 0.0} {"seed": 1156, "task": "acde_medium", "difficulty": "medium", "step": 2, "state": {"patient_condition": "serious", "remaining_time_minutes": 17.0, "failed_hospitals": ["H2"], "visited_hospitals": ["H2"], "ambulance_status": "rerouting"}, "action": {"hospital_id": "H3", "policy_score": 0.43375042795251284, "strategy": "risk-aware policy"}, "outcome": {"status": "REJECTED", "reason": "Condition became non-transferable during delay; immediate critical care failed"}, "reward": 0.08} {"seed": 1157, "task": "acde_hard", "difficulty": "hard", "step": 1, "state": {"patient_condition": "critical", "remaining_time_minutes": 11.0, "failed_hospitals": [], "visited_hospitals": [], "ambulance_status": "en_route"}, "action": {"hospital_id": "H1", "policy_score": 0.3824107913208125, "strategy": "safe policy + critical triage"}, "outcome": {"status": "REJECTED", "reason": "Hospital cannot admit: No specialist available, Hospital overloaded"}, "reward": 0.0} {"seed": 1157, "task": "acde_hard", "difficulty": "hard", "step": 2, "state": {"patient_condition": "critical", "remaining_time_minutes": 11.0, "failed_hospitals": ["H1"], "visited_hospitals": ["H1"], "ambulance_status": "rerouting"}, "action": {"hospital_id": "H5", "policy_score": 0.3715441859415079, "strategy": "risk-aware policy"}, "outcome": {"status": "REJECTED", "reason": "Hospital cannot admit: No specialist available"}, "reward": 0.11} {"seed": 1157, "task": "acde_hard", "difficulty": "hard", "step": 3, "state": {"patient_condition": "critical", "remaining_time_minutes": 11.0, "failed_hospitals": ["H1", "H5"], "visited_hospitals": ["H1", "H5"], "ambulance_status": "rerouting"}, "action": {"hospital_id": "H6", "policy_score": 0.4275606482618861, "strategy": "risk-aware policy"}, "outcome": {"status": "REJECTED", "reason": "Hidden mismatch at arrival (wrong risky guess). Rerouting required."}, "reward": 0.0} {"seed": 1157, "task": "acde_hard", "difficulty": "hard", "step": 4, "state": {"patient_condition": "critical", "remaining_time_minutes": 11.0, "failed_hospitals": ["H1", "H5", "H4"], "visited_hospitals": ["H1", "H5", "H4"], "ambulance_status": "rerouting"}, "action": {"hospital_id": "H5", "policy_score": 0.4120157792445422, "strategy": "risk-aware policy + immediate-retry override"}, "outcome": {"status": "REJECTED", "reason": "Hospital cannot admit: ICU unavailable, No specialist available"}, "reward": 0.0} {"seed": 1255, "task": "acde_easy", "difficulty": "easy", "step": 1, "state": {"patient_condition": "serious", "remaining_time_minutes": 20.0, "failed_hospitals": [], "visited_hospitals": [], "ambulance_status": "en_route"}, "action": {"hospital_id": "H1", "policy_score": 0.3076919065858667, "strategy": "safe policy"}, "outcome": {"status": "ACCEPTED", "reason": "Patient stabilized after delayed admission"}, "reward": 0.8880000000000001} {"seed": 1256, "task": "acde_medium", "difficulty": "medium", "step": 1, "state": {"patient_condition": "serious", "remaining_time_minutes": 17.0, "failed_hospitals": [], "visited_hospitals": [], "ambulance_status": "en_route"}, "action": {"hospital_id": "H2", "policy_score": 0.3135757943277168, "strategy": "safe policy"}, "outcome": {"status": "REJECTED", "reason": "Hidden mismatch at arrival (wrong risky guess). Rerouting required."}, "reward": 0.0} {"seed": 1256, "task": "acde_medium", "difficulty": "medium", "step": 2, "state": {"patient_condition": "unstable", "remaining_time_minutes": 17.0, "failed_hospitals": ["H2"], "visited_hospitals": ["H2"], "ambulance_status": "rerouting"}, "action": {"hospital_id": "H3", "policy_score": 0.4783480373464987, "strategy": "risk-aware policy"}, "outcome": {"status": "PARTIAL", "reason": "Admitted with significant risk: No specialist available"}, "reward": 0.27} {"seed": 1256, "task": "acde_medium", "difficulty": "medium", "step": 3, "state": {"patient_condition": "critical", "remaining_time_minutes": 17.0, "failed_hospitals": ["H2"], "visited_hospitals": ["H2", "H3"], "ambulance_status": "in_transit"}, "action": {"hospital_id": "H3", "policy_score": 0.32133173629232054, "strategy": "balanced policy + critical triage + anti-stupidity guard"}, "outcome": {"status": "REJECTED", "reason": "Hospital cannot admit: No specialist available"}, "reward": 0.0} {"seed": 1256, "task": "acde_medium", "difficulty": "medium", "step": 4, "state": {"patient_condition": "critical", "remaining_time_minutes": 17.0, "failed_hospitals": ["H2", "H3"], "visited_hospitals": ["H2", "H3"], "ambulance_status": "rerouting"}, "action": {"hospital_id": "H1", "policy_score": 0.024949439699236232, "strategy": "risk-aware policy"}, "outcome": {"status": "ACCEPTED", "reason": "Emergency stabilization at last attempt"}, "reward": 0.704} {"seed": 1257, "task": "acde_hard", "difficulty": "hard", "step": 1, "state": {"patient_condition": "critical", "remaining_time_minutes": 13.0, "failed_hospitals": [], "visited_hospitals": [], "ambulance_status": "en_route"}, "action": {"hospital_id": "H2", "policy_score": 0.3332698032184948, "strategy": "safe policy + critical triage"}, "outcome": {"status": "REJECTED", "reason": "Hospital cannot admit: Hospital overloaded"}, "reward": 0.0} {"seed": 1257, "task": "acde_hard", "difficulty": "hard", "step": 2, "state": {"patient_condition": "critical", "remaining_time_minutes": 13.0, "failed_hospitals": ["H2"], "visited_hospitals": ["H2"], "ambulance_status": "rerouting"}, "action": {"hospital_id": "H5", "policy_score": 0.23864191009204766, "strategy": "risk-aware policy"}, "outcome": {"status": "REJECTED", "reason": "Hospital cannot admit: ICU unavailable, No specialist available"}, "reward": 0.0} {"seed": 1257, "task": "acde_hard", "difficulty": "hard", "step": 3, "state": {"patient_condition": "critical", "remaining_time_minutes": 13.0, "failed_hospitals": ["H2", "H5"], "visited_hospitals": ["H2", "H5"], "ambulance_status": "rerouting"}, "action": {"hospital_id": "H6", "policy_score": 0.30050095304392616, "strategy": "risk-aware policy"}, "outcome": {"status": "PARTIAL", "reason": "Critical deterioration managed temporarily; reroute still needed"}, "reward": 0.215} {"seed": 1257, "task": "acde_hard", "difficulty": "hard", "step": 4, "state": {"patient_condition": "unstable", "remaining_time_minutes": 13.0, "failed_hospitals": ["H2", "H5"], "visited_hospitals": ["H2", "H5", "H6"], "ambulance_status": "in_transit"}, "action": {"hospital_id": "H3", "policy_score": 0.4153583275064572, "strategy": "balanced policy"}, "outcome": {"status": "REJECTED", "reason": "Hidden mismatch at arrival (wrong risky guess). Rerouting required."}, "reward": 0.0} {"seed": 1355, "task": "acde_easy", "difficulty": "easy", "step": 1, "state": {"patient_condition": "critical", "remaining_time_minutes": 16.0, "failed_hospitals": [], "visited_hospitals": [], "ambulance_status": "en_route"}, "action": {"hospital_id": "H1", "policy_score": 0.3026111353721816, "strategy": "safe policy + critical triage"}, "outcome": {"status": "ACCEPTED", "reason": "Patient admitted and treatment began"}, "reward": 0.94} {"seed": 1356, "task": "acde_medium", "difficulty": "medium", "step": 1, "state": {"patient_condition": "critical", "remaining_time_minutes": 14.0, "failed_hospitals": [], "visited_hospitals": [], "ambulance_status": "en_route"}, "action": {"hospital_id": "H2", "policy_score": 0.4747855543287844, "strategy": "safe policy"}, "outcome": {"status": "PARTIAL", "reason": "Admitted with delays: equipment issue"}, "reward": 0.3500000000000001} {"seed": 1356, "task": "acde_medium", "difficulty": "medium", "step": 2, "state": {"patient_condition": "critical", "remaining_time_minutes": 14.0, "failed_hospitals": [], "visited_hospitals": ["H2"], "ambulance_status": "in_transit"}, "action": {"hospital_id": "H2", "policy_score": 0.47392246834349305, "strategy": "balanced policy + anti-stupidity guard"}, "outcome": {"status": "REJECTED", "reason": "Condition became non-transferable during delay; immediate critical care failed"}, "reward": 0.0} {"seed": 1357, "task": "acde_hard", "difficulty": "hard", "step": 1, "state": {"patient_condition": "critical", "remaining_time_minutes": 12.0, "failed_hospitals": [], "visited_hospitals": [], "ambulance_status": "en_route"}, "action": {"hospital_id": "H5", "policy_score": 0.43599855606358745, "strategy": "safe policy + critical triage"}, "outcome": {"status": "REJECTED", "reason": "Hospital cannot admit: Hospital overloaded"}, "reward": 0.07} {"seed": 1357, "task": "acde_hard", "difficulty": "hard", "step": 2, "state": {"patient_condition": "critical", "remaining_time_minutes": 12.0, "failed_hospitals": ["H5"], "visited_hospitals": ["H5"], "ambulance_status": "rerouting"}, "action": {"hospital_id": "H6", "policy_score": 0.4321782104049002, "strategy": "risk-aware policy"}, "outcome": {"status": "REJECTED", "reason": "Hospital cannot admit: Hospital overloaded"}, "reward": 0.0} {"seed": 1357, "task": "acde_hard", "difficulty": "hard", "step": 3, "state": {"patient_condition": "critical", "remaining_time_minutes": 12.0, "failed_hospitals": ["H5", "H6"], "visited_hospitals": ["H5", "H6"], "ambulance_status": "rerouting"}, "action": {"hospital_id": "H1", "policy_score": 0.046420839879205415, "strategy": "risk-aware policy + anti-stupidity guard"}, "outcome": {"status": "PARTIAL", "reason": "Critical deterioration managed temporarily; reroute still needed"}, "reward": 0.095} {"seed": 1357, "task": "acde_hard", "difficulty": "hard", "step": 4, "state": {"patient_condition": "critical", "remaining_time_minutes": 12.0, "failed_hospitals": ["H5", "H6"], "visited_hospitals": ["H5", "H6", "H3"], "ambulance_status": "in_transit"}, "action": {"hospital_id": "H2", "policy_score": 0.4594408448355545, "strategy": "balanced policy + critical triage"}, "outcome": {"status": "PARTIAL", "reason": "Condition worsened but remains temporarily transferable"}, "reward": 0.17500000000000002} {"seed": 1455, "task": "acde_easy", "difficulty": "easy", "step": 1, "state": {"patient_condition": "serious", "remaining_time_minutes": 18.0, "failed_hospitals": [], "visited_hospitals": [], "ambulance_status": "en_route"}, "action": {"hospital_id": "H3", "policy_score": 0.2969558878458098, "strategy": "safe policy"}, "outcome": {"status": "ACCEPTED", "reason": "Patient admitted and treatment began"}, "reward": 1.0} {"seed": 1456, "task": "acde_medium", "difficulty": "medium", "step": 1, "state": {"patient_condition": "critical", "remaining_time_minutes": 14.0, "failed_hospitals": [], "visited_hospitals": [], "ambulance_status": "en_route"}, "action": {"hospital_id": "H2", "policy_score": 0.4995107296329243, "strategy": "safe policy"}, "outcome": {"status": "REJECTED", "reason": "Emergency beds became unavailable during arrival"}, "reward": 0.0} {"seed": 1456, "task": "acde_medium", "difficulty": "medium", "step": 2, "state": {"patient_condition": "critical", "remaining_time_minutes": 14.0, "failed_hospitals": ["H2"], "visited_hospitals": ["H2"], "ambulance_status": "rerouting"}, "action": {"hospital_id": "H1", "policy_score": 0.17338051521433662, "strategy": "risk-aware policy"}, "outcome": {"status": "REJECTED", "reason": "Condition became non-transferable during delay; immediate critical care failed"}, "reward": 0.009999999999999995} {"seed": 1457, "task": "acde_hard", "difficulty": "hard", "step": 1, "state": {"patient_condition": "critical", "remaining_time_minutes": 11.0, "failed_hospitals": [], "visited_hospitals": [], "ambulance_status": "en_route"}, "action": {"hospital_id": "H6", "policy_score": 0.36713886877040014, "strategy": "safe policy + critical triage + anti-stupidity guard"}, "outcome": {"status": "PARTIAL", "reason": "Admitted with significant risk: ICU unavailable"}, "reward": 0.17} {"seed": 1457, "task": "acde_hard", "difficulty": "hard", "step": 2, "state": {"patient_condition": "critical", "remaining_time_minutes": 11.0, "failed_hospitals": [], "visited_hospitals": ["H3"], "ambulance_status": "in_transit"}, "action": {"hospital_id": "H6", "policy_score": 0.3506385430763287, "strategy": "balanced policy + critical triage"}, "outcome": {"status": "REJECTED", "reason": "Hospital cannot admit: No specialist available, Hospital overloaded"}, "reward": 0.0} {"seed": 1457, "task": "acde_hard", "difficulty": "hard", "step": 3, "state": {"patient_condition": "critical", "remaining_time_minutes": 11.0, "failed_hospitals": ["H6"], "visited_hospitals": ["H3", "H6"], "ambulance_status": "rerouting"}, "action": {"hospital_id": "H5", "policy_score": 0.2639800067748549, "strategy": "risk-aware policy"}, "outcome": {"status": "REJECTED", "reason": "Hospital cannot admit: Hospital overloaded"}, "reward": 0.0} {"seed": 1457, "task": "acde_hard", "difficulty": "hard", "step": 4, "state": {"patient_condition": "critical", "remaining_time_minutes": 11.0, "failed_hospitals": ["H6", "H5"], "visited_hospitals": ["H3", "H6", "H5"], "ambulance_status": "rerouting"}, "action": {"hospital_id": "H1", "policy_score": 0.38666042100358916, "strategy": "risk-aware policy + anti-stupidity guard"}, "outcome": {"status": "REJECTED", "reason": "Hospital cannot admit: ICU unavailable, No specialist available"}, "reward": 0.0} {"seed": 555, "task": "acde_medium", "difficulty": "medium", "step": 1, "state": {"patient_condition": "critical", "remaining_time_minutes": 14.0, "failed_hospitals": [], "visited_hospitals": [], "ambulance_status": "en_route"}, "action": {"hospital_id": "H2", "policy_score": 0.49360516466883797, "strategy": "safe policy + critical triage"}, "outcome": {"status": "PARTIAL", "reason": "Admitted with delays: prolonged transfer strain"}, "reward": 0.4000000000000001} {"seed": 555, "task": "acde_medium", "difficulty": "medium", "step": 2, "state": {"patient_condition": "critical", "remaining_time_minutes": 14.0, "failed_hospitals": [], "visited_hospitals": ["H2"], "ambulance_status": "in_transit"}, "action": {"hospital_id": "H2", "policy_score": 0.4628907945739484, "strategy": "balanced policy + anti-stupidity guard"}, "outcome": {"status": "ACCEPTED", "reason": "Patient stabilized after critical delay"}, "reward": 0.4756000000000001} {"seed": 555, "task": "acde_medium", "difficulty": "medium", "step": 1, "state": {"patient_condition": "critical", "remaining_time_minutes": 14.0, "failed_hospitals": [], "visited_hospitals": [], "ambulance_status": "en_route"}, "action": {"hospital_id": "H2", "policy_score": 0.4941255067384057, "strategy": "best-route retain"}, "outcome": {"status": "PARTIAL", "reason": "Admitted with delays: prolonged transfer strain"}, "reward": 0.4000000000000001} {"seed": 555, "task": "acde_medium", "difficulty": "medium", "step": 2, "state": {"patient_condition": "critical", "remaining_time_minutes": 14.0, "failed_hospitals": [], "visited_hospitals": ["H2"], "ambulance_status": "in_transit"}, "action": {"hospital_id": "H2", "policy_score": 0.4628908411535494, "strategy": "balanced policy + anti-stupidity guard"}, "outcome": {"status": "ACCEPTED", "reason": "Patient stabilized after critical delay"}, "reward": 0.4756000000000001} {"seed": 553093117, "task": "acde_medium", "difficulty": "medium", "step": 1, "state": {"patient_condition": "critical", "remaining_time_minutes": 15.0, "failed_hospitals": [], "visited_hospitals": [], "ambulance_status": "en_route"}, "action": {"hospital_id": "H5", "policy_score": 0.3680683906259111, "strategy": "safe policy + critical triage + anti-stupidity guard"}, "outcome": {"status": "ACCEPTED", "reason": "Patient admitted and treatment began"}, "reward": 0.8200000000000001} {"seed": 896528413, "task": "acde_medium", "difficulty": "medium", "step": 1, "state": {"patient_condition": "critical", "remaining_time_minutes": 15.0, "failed_hospitals": [], "visited_hospitals": [], "ambulance_status": "en_route"}, "action": {"hospital_id": "H5", "policy_score": 0.37611449062446184, "strategy": "safe policy + critical triage"}, "outcome": {"status": "ACCEPTED", "reason": "Patient admitted and treatment began"}, "reward": 0.9500000000000001} {"seed": 877427547, "task": "acde_medium", "difficulty": "medium", "step": 1, "state": {"patient_condition": "serious", "remaining_time_minutes": 17.0, "failed_hospitals": [], "visited_hospitals": [], "ambulance_status": "en_route"}, "action": {"hospital_id": "H2", "policy_score": 0.36188794963141646, "strategy": "safe policy + anti-stupidity guard"}, "outcome": {"status": "PARTIAL", "reason": "Early rejection mitigated by emergency field stabilization"}, "reward": 0.30500000000000005} {"seed": 877427547, "task": "acde_medium", "difficulty": "medium", "step": 2, "state": {"patient_condition": "stable", "remaining_time_minutes": 17.0, "failed_hospitals": [], "visited_hospitals": ["H5"], "ambulance_status": "in_transit"}, "action": {"hospital_id": "H2", "policy_score": 0.3072909645996028, "strategy": "balanced policy"}, "outcome": {"status": "ACCEPTED", "reason": "Patient stabilized after critical delay"}, "reward": 0.6956000000000001} {"seed": 894675818, "task": "acde_easy", "difficulty": "easy", "step": 1, "state": {"patient_condition": "serious", "remaining_time_minutes": 20.0, "failed_hospitals": [], "visited_hospitals": [], "ambulance_status": "en_route"}, "action": {"hospital_id": "H1", "policy_score": 0.18305924369121576, "strategy": "safe policy"}, "outcome": {"status": "REJECTED", "reason": "Hospital cannot admit: ICU unavailable"}, "reward": 0.14} {"seed": 894675818, "task": "acde_easy", "difficulty": "easy", "step": 2, "state": {"patient_condition": "serious", "remaining_time_minutes": 20.0, "failed_hospitals": ["H1"], "visited_hospitals": ["H1"], "ambulance_status": "rerouting"}, "action": {"hospital_id": "H4", "policy_score": 0.38540984922844335, "strategy": "risk-aware policy"}, "outcome": {"status": "ACCEPTED", "reason": "Patient admitted and treatment began"}, "reward": 1.0} {"seed": 894675819, "task": "acde_medium", "difficulty": "medium", "step": 1, "state": {"patient_condition": "serious", "remaining_time_minutes": 17.0, "failed_hospitals": [], "visited_hospitals": [], "ambulance_status": "en_route"}, "action": {"hospital_id": "H2", "policy_score": 0.33097956010045465, "strategy": "safe policy"}, "outcome": {"status": "PARTIAL", "reason": "Admitted with delays: prolonged transfer strain"}, "reward": 0.44000000000000006} {"seed": 894675819, "task": "acde_medium", "difficulty": "medium", "step": 2, "state": {"patient_condition": "unstable", "remaining_time_minutes": 17.0, "failed_hospitals": [], "visited_hospitals": ["H2"], "ambulance_status": "in_transit"}, "action": {"hospital_id": "H3", "policy_score": 0.33411271736246334, "strategy": "balanced policy + critical triage"}, "outcome": {"status": "REJECTED", "reason": "Condition became irreversible after delays"}, "reward": 0.11} {"seed": 894675819, "task": "acde_medium", "difficulty": "medium", "step": 3, "state": {"patient_condition": "unstable", "remaining_time_minutes": 17.0, "failed_hospitals": ["H4"], "visited_hospitals": ["H2", "H4"], "ambulance_status": "rerouting"}, "action": {"hospital_id": "H2", "policy_score": 0.12971841445220822, "strategy": "risk-aware policy + immediate-retry override"}, "outcome": {"status": "REJECTED", "reason": "Condition became non-transferable during delay; immediate critical care failed"}, "reward": 0.0} {"seed": 894675820, "task": "acde_hard", "difficulty": "hard", "step": 1, "state": {"patient_condition": "critical", "remaining_time_minutes": 12.0, "failed_hospitals": [], "visited_hospitals": [], "ambulance_status": "en_route"}, "action": {"hospital_id": "H2", "policy_score": 0.22086318138780767, "strategy": "safe policy"}, "outcome": {"status": "REJECTED", "reason": "Hospital cannot admit: ICU unavailable, Hospital overloaded"}, "reward": 0.0} {"seed": 894675820, "task": "acde_hard", "difficulty": "hard", "step": 2, "state": {"patient_condition": "critical", "remaining_time_minutes": 12.0, "failed_hospitals": ["H2"], "visited_hospitals": ["H2"], "ambulance_status": "rerouting"}, "action": {"hospital_id": "H3", "policy_score": 0.12565735415854704, "strategy": "risk-aware policy + anti-stupidity guard"}, "outcome": {"status": "REJECTED", "reason": "Hospital cannot admit: No specialist available"}, "reward": 0.0} {"seed": 894675820, "task": "acde_hard", "difficulty": "hard", "step": 3, "state": {"patient_condition": "critical", "remaining_time_minutes": 12.0, "failed_hospitals": ["H2", "H3"], "visited_hospitals": ["H2", "H3"], "ambulance_status": "rerouting"}, "action": {"hospital_id": "H6", "policy_score": 0.11518464278270465, "strategy": "risk-aware policy + guided-exploration"}, "outcome": {"status": "REJECTED", "reason": "Hospital cannot admit: ICU unavailable, No specialist available"}, "reward": 0.11} {"seed": 894675820, "task": "acde_hard", "difficulty": "hard", "step": 4, "state": {"patient_condition": "critical", "remaining_time_minutes": 12.0, "failed_hospitals": ["H2", "H3", "H6"], "visited_hospitals": ["H2", "H3", "H6"], "ambulance_status": "rerouting"}, "action": {"hospital_id": "H4", "policy_score": 0.11979326699339597, "strategy": "risk-aware policy"}, "outcome": {"status": "PARTIAL", "reason": "Critical deterioration managed temporarily; reroute still needed"}, "reward": 0.215} {"seed": 123, "task": "acde_easy", "difficulty": "easy", "step": 1, "state": {"patient_condition": "serious", "remaining_time_minutes": 20.0, "failed_hospitals": [], "visited_hospitals": [], "ambulance_status": "en_route"}, "action": {"hospital_id": "H1", "policy_score": 0.38513944081914836, "strategy": "safe policy + guided-exploration"}, "outcome": {"status": "ACCEPTED", "reason": "Patient admitted and treatment began"}, "reward": 1.0} {"seed": 124, "task": "acde_medium", "difficulty": "medium", "step": 1, "state": {"patient_condition": "critical", "remaining_time_minutes": 14.0, "failed_hospitals": [], "visited_hospitals": [], "ambulance_status": "en_route"}, "action": {"hospital_id": "H3", "policy_score": 0.2542313592519237, "strategy": "safe policy + critical triage"}, "outcome": {"status": "PARTIAL", "reason": "Critical deterioration managed temporarily; reroute still needed"}, "reward": 0.26500000000000007} {"seed": 124, "task": "acde_medium", "difficulty": "medium", "step": 2, "state": {"patient_condition": "unstable", "remaining_time_minutes": 14.0, "failed_hospitals": [], "visited_hospitals": ["H3"], "ambulance_status": "in_transit"}, "action": {"hospital_id": "H2", "policy_score": 0.28564476176964476, "strategy": "balanced policy + critical triage"}, "outcome": {"status": "REJECTED", "reason": "Condition relapsed after temporary stabilization"}, "reward": 0.1} {"seed": 124, "task": "acde_medium", "difficulty": "medium", "step": 3, "state": {"patient_condition": "unstable", "remaining_time_minutes": 14.0, "failed_hospitals": ["H1"], "visited_hospitals": ["H3", "H1"], "ambulance_status": "rerouting"}, "action": {"hospital_id": "H5", "policy_score": 0.2676381567105855, "strategy": "risk-aware policy + immediate-retry override"}, "outcome": {"status": "REJECTED", "reason": "Hospital cannot admit: Hospital overloaded"}, "reward": 0.07} {"seed": 124, "task": "acde_medium", "difficulty": "medium", "step": 4, "state": {"patient_condition": "unstable", "remaining_time_minutes": 14.0, "failed_hospitals": ["H1", "H5"], "visited_hospitals": ["H3", "H1", "H5"], "ambulance_status": "rerouting"}, "action": {"hospital_id": "H2", "policy_score": 0.4602097000108944, "strategy": "risk-aware policy"}, "outcome": {"status": "ACCEPTED", "reason": "Emergency stabilization at last attempt"}, "reward": 0.5840000000000001} {"seed": 125, "task": "acde_hard", "difficulty": "hard", "step": 1, "state": {"patient_condition": "critical", "remaining_time_minutes": 11.0, "failed_hospitals": [], "visited_hospitals": [], "ambulance_status": "en_route"}, "action": {"hospital_id": "H2", "policy_score": 0.24347869935725594, "strategy": "safe policy + critical triage"}, "outcome": {"status": "REJECTED", "reason": "Hospital cannot admit: Hospital overloaded"}, "reward": 0.0} {"seed": 125, "task": "acde_hard", "difficulty": "hard", "step": 2, "state": {"patient_condition": "critical", "remaining_time_minutes": 11.0, "failed_hospitals": ["H2"], "visited_hospitals": ["H2"], "ambulance_status": "rerouting"}, "action": {"hospital_id": "H1", "policy_score": 0.399222905770927, "strategy": "risk-aware policy + anti-stupidity guard"}, "outcome": {"status": "REJECTED", "reason": "Hidden mismatch at arrival (wrong risky guess). Rerouting required."}, "reward": 0.0} {"seed": 125, "task": "acde_hard", "difficulty": "hard", "step": 3, "state": {"patient_condition": "critical", "remaining_time_minutes": 11.0, "failed_hospitals": ["H2", "H4"], "visited_hospitals": ["H2", "H4"], "ambulance_status": "rerouting"}, "action": {"hospital_id": "H3", "policy_score": 0.08687123376577266, "strategy": "risk-aware policy + immediate-retry override"}, "outcome": {"status": "ACCEPTED", "reason": "Condition stabilized after progressive treatment"}, "reward": 0.4640000000000001} {"seed": 123, "task": "acde_easy", "difficulty": "easy", "step": 1, "state": {"patient_condition": "serious", "remaining_time_minutes": 20.0, "failed_hospitals": [], "visited_hospitals": [], "ambulance_status": "en_route"}, "action": {"hospital_id": "H1", "policy_score": 0.3997022038653544, "strategy": "best-route retain"}, "outcome": {"status": "ACCEPTED", "reason": "Patient admitted and treatment began"}, "reward": 0.999} {"seed": 124, "task": "acde_medium", "difficulty": "medium", "step": 1, "state": {"patient_condition": "critical", "remaining_time_minutes": 14.0, "failed_hospitals": [], "visited_hospitals": [], "ambulance_status": "en_route"}, "action": {"hospital_id": "H3", "policy_score": 0.25891360812102787, "strategy": "best-route retain"}, "outcome": {"status": "PARTIAL", "reason": "Critical deterioration managed temporarily; reroute still needed"}, "reward": 0.26500000000000007} {"seed": 124, "task": "acde_medium", "difficulty": "medium", "step": 2, "state": {"patient_condition": "unstable", "remaining_time_minutes": 14.0, "failed_hospitals": [], "visited_hospitals": ["H3"], "ambulance_status": "in_transit"}, "action": {"hospital_id": "H2", "policy_score": 0.3007912164646373, "strategy": "best-route retain"}, "outcome": {"status": "REJECTED", "reason": "Condition relapsed after temporary stabilization"}, "reward": 0.1} {"seed": 124, "task": "acde_medium", "difficulty": "medium", "step": 3, "state": {"patient_condition": "unstable", "remaining_time_minutes": 14.0, "failed_hospitals": ["H1"], "visited_hospitals": ["H3", "H1"], "ambulance_status": "rerouting"}, "action": {"hospital_id": "H5", "policy_score": 0.28052648402402824, "strategy": "risk-aware policy + immediate-retry override"}, "outcome": {"status": "REJECTED", "reason": "Hospital cannot admit: Hospital overloaded"}, "reward": 0.07} {"seed": 124, "task": "acde_medium", "difficulty": "medium", "step": 4, "state": {"patient_condition": "unstable", "remaining_time_minutes": 14.0, "failed_hospitals": ["H1", "H5"], "visited_hospitals": ["H3", "H1", "H5"], "ambulance_status": "rerouting"}, "action": {"hospital_id": "H2", "policy_score": 0.4602176574461837, "strategy": "risk-aware policy"}, "outcome": {"status": "ACCEPTED", "reason": "Emergency stabilization at last attempt"}, "reward": 0.5840000000000001} {"seed": 125, "task": "acde_hard", "difficulty": "hard", "step": 1, "state": {"patient_condition": "critical", "remaining_time_minutes": 11.0, "failed_hospitals": [], "visited_hospitals": [], "ambulance_status": "en_route"}, "action": {"hospital_id": "H2", "policy_score": 0.24347869935725594, "strategy": "best-route retain"}, "outcome": {"status": "REJECTED", "reason": "Hospital cannot admit: Hospital overloaded"}, "reward": 0.001} {"seed": 125, "task": "acde_hard", "difficulty": "hard", "step": 2, "state": {"patient_condition": "critical", "remaining_time_minutes": 11.0, "failed_hospitals": ["H2"], "visited_hospitals": ["H2"], "ambulance_status": "rerouting"}, "action": {"hospital_id": "H1", "policy_score": 0.39922290989538656, "strategy": "risk-aware policy + anti-stupidity guard"}, "outcome": {"status": "REJECTED", "reason": "Hidden mismatch at arrival (wrong risky guess). Rerouting required."}, "reward": 0.001} {"seed": 125, "task": "acde_hard", "difficulty": "hard", "step": 3, "state": {"patient_condition": "critical", "remaining_time_minutes": 11.0, "failed_hospitals": ["H2", "H4"], "visited_hospitals": ["H2", "H4"], "ambulance_status": "rerouting"}, "action": {"hospital_id": "H3", "policy_score": 0.08687125701068692, "strategy": "risk-aware policy + anti-stupidity guard + immediate-retry override"}, "outcome": {"status": "ACCEPTED", "reason": "Condition stabilized after progressive treatment"}, "reward": 0.4640000000000001} {"seed": 42, "task": "acde_easy", "difficulty": "easy", "step": 1, "state": {"patient_condition": "serious", "remaining_time_minutes": 18.0, "failed_hospitals": [], "visited_hospitals": [], "ambulance_status": "en_route"}, "action": {"hospital_id": "H1", "policy_score": 0.2700762940680355, "strategy": "safe policy"}, "outcome": {"status": "ACCEPTED", "reason": "Patient admitted and treatment began"}, "reward": 0.999} {"seed": 43, "task": "acde_medium", "difficulty": "medium", "step": 1, "state": {"patient_condition": "critical", "remaining_time_minutes": 14.0, "failed_hospitals": [], "visited_hospitals": [], "ambulance_status": "en_route"}, "action": {"hospital_id": "H2", "policy_score": 0.3231158217480875, "strategy": "safe policy + critical triage + guided-exploration"}, "outcome": {"status": "REJECTED", "reason": "Condition became non-transferable during delay; immediate critical care failed"}, "reward": 0.109} {"seed": 44, "task": "acde_hard", "difficulty": "hard", "step": 1, "state": {"patient_condition": "critical", "remaining_time_minutes": 13.0, "failed_hospitals": [], "visited_hospitals": [], "ambulance_status": "en_route"}, "action": {"hospital_id": "H5", "policy_score": 0.4862574941416685, "strategy": "safe policy + critical triage"}, "outcome": {"status": "REJECTED", "reason": "Hospital cannot admit: ICU unavailable"}, "reward": 0.001} {"seed": 44, "task": "acde_hard", "difficulty": "hard", "step": 2, "state": {"patient_condition": "critical", "remaining_time_minutes": 13.0, "failed_hospitals": ["H2"], "visited_hospitals": ["H2"], "ambulance_status": "rerouting"}, "action": {"hospital_id": "H2", "policy_score": 0.07027740357273131, "strategy": "risk-aware policy + immediate-retry override"}, "outcome": {"status": "REJECTED", "reason": "Hidden mismatch at arrival (wrong risky guess). Rerouting required."}, "reward": 0.001} {"seed": 44, "task": "acde_hard", "difficulty": "hard", "step": 3, "state": {"patient_condition": "critical", "remaining_time_minutes": 13.0, "failed_hospitals": ["H2"], "visited_hospitals": ["H2"], "ambulance_status": "rerouting"}, "action": {"hospital_id": "H5", "policy_score": 0.47341627825998767, "strategy": "risk-aware policy"}, "outcome": {"status": "REJECTED", "reason": "Condition became non-transferable during delay; immediate critical care failed"}, "reward": 0.001} {"seed": 865967163, "task": "acde_easy", "difficulty": "easy", "step": 1, "state": {"patient_condition": "serious", "remaining_time_minutes": 20.0, "failed_hospitals": [], "visited_hospitals": [], "ambulance_status": "en_route"}, "action": {"hospital_id": "H4", "policy_score": 0.28522225923842554, "strategy": "safe policy"}, "outcome": {"status": "PARTIAL", "reason": "Critical deterioration managed temporarily; reroute still needed"}, "reward": 0.274} {"seed": 865967163, "task": "acde_easy", "difficulty": "easy", "step": 2, "state": {"patient_condition": "stable", "remaining_time_minutes": 20.0, "failed_hospitals": [], "visited_hospitals": ["H4"], "ambulance_status": "in_transit"}, "action": {"hospital_id": "H1", "policy_score": 0.430398797272352, "strategy": "balanced policy"}, "outcome": {"status": "ACCEPTED", "reason": "Patient stabilized after delayed admission"}, "reward": 0.8960000000000001} {"seed": 865967164, "task": "acde_medium", "difficulty": "medium", "step": 1, "state": {"patient_condition": "serious", "remaining_time_minutes": 17.0, "failed_hospitals": [], "visited_hospitals": [], "ambulance_status": "en_route"}, "action": {"hospital_id": "H3", "policy_score": 0.3470070739535391, "strategy": "safe policy + anti-stupidity guard"}, "outcome": {"status": "PARTIAL", "reason": "Admitted with delays: doctor delayed"}, "reward": 0.4690000000000001} {"seed": 865967164, "task": "acde_medium", "difficulty": "medium", "step": 2, "state": {"patient_condition": "serious", "remaining_time_minutes": 17.0, "failed_hospitals": [], "visited_hospitals": ["H3"], "ambulance_status": "in_transit"}, "action": {"hospital_id": "H2", "policy_score": 0.3155267186726896, "strategy": "balanced policy + anti-stupidity guard"}, "outcome": {"status": "REJECTED", "reason": "Hospital cannot admit: ICU unavailable"}, "reward": 0.079} {"seed": 865967164, "task": "acde_medium", "difficulty": "medium", "step": 3, "state": {"patient_condition": "serious", "remaining_time_minutes": 17.0, "failed_hospitals": ["H2"], "visited_hospitals": ["H3", "H2"], "ambulance_status": "rerouting"}, "action": {"hospital_id": "H3", "policy_score": 0.4258905882454945, "strategy": "risk-aware policy + anti-stupidity guard"}, "outcome": {"status": "ACCEPTED", "reason": "Condition stabilized after progressive treatment"}, "reward": 0.532} {"seed": 865967165, "task": "acde_hard", "difficulty": "hard", "step": 1, "state": {"patient_condition": "critical", "remaining_time_minutes": 13.0, "failed_hospitals": [], "visited_hospitals": [], "ambulance_status": "en_route"}, "action": {"hospital_id": "H6", "policy_score": 0.3076474962108312, "strategy": "safe policy + critical triage"}, "outcome": {"status": "REJECTED", "reason": "Hospital cannot admit: ICU unavailable"}, "reward": 0.001} {"seed": 865967165, "task": "acde_hard", "difficulty": "hard", "step": 2, "state": {"patient_condition": "critical", "remaining_time_minutes": 13.0, "failed_hospitals": ["H6"], "visited_hospitals": ["H6"], "ambulance_status": "rerouting"}, "action": {"hospital_id": "H2", "policy_score": 0.3035629436259161, "strategy": "risk-aware policy + guided-exploration"}, "outcome": {"status": "REJECTED", "reason": "Hospital cannot admit: No specialist available"}, "reward": 0.001} {"seed": 865967165, "task": "acde_hard", "difficulty": "hard", "step": 3, "state": {"patient_condition": "critical", "remaining_time_minutes": 13.0, "failed_hospitals": ["H6", "H4"], "visited_hospitals": ["H6", "H4"], "ambulance_status": "rerouting"}, "action": {"hospital_id": "H6", "policy_score": 0.11129517908464792, "strategy": "risk-aware policy + immediate-retry override"}, "outcome": {"status": "REJECTED", "reason": "Hidden mismatch at arrival (wrong risky guess). Rerouting required."}, "reward": 0.001} {"seed": 865967165, "task": "acde_hard", "difficulty": "hard", "step": 4, "state": {"patient_condition": "critical", "remaining_time_minutes": 13.0, "failed_hospitals": ["H6", "H4"], "visited_hospitals": ["H6", "H4"], "ambulance_status": "rerouting"}, "action": {"hospital_id": "H3", "policy_score": 0.29586549899480935, "strategy": "risk-aware policy + anti-stupidity guard"}, "outcome": {"status": "REJECTED", "reason": "Hidden mismatch at arrival (wrong risky guess). Rerouting required."}, "reward": 0.001} {"seed": 562874771, "task": "acde_easy", "difficulty": "easy", "step": 1, "state": {"patient_condition": "critical", "remaining_time_minutes": 16.0, "failed_hospitals": [], "visited_hospitals": [], "ambulance_status": "en_route"}, "action": {"hospital_id": "H4", "policy_score": 0.2712048097577652, "strategy": "safe policy + critical triage"}, "outcome": {"status": "PARTIAL", "reason": "Critical deterioration managed temporarily; reroute still needed"}, "reward": 0.234} {"seed": 562874771, "task": "acde_easy", "difficulty": "easy", "step": 2, "state": {"patient_condition": "critical", "remaining_time_minutes": 16.0, "failed_hospitals": [], "visited_hospitals": ["H4"], "ambulance_status": "in_transit"}, "action": {"hospital_id": "H1", "policy_score": 0.35970778218903066, "strategy": "balanced policy + critical triage"}, "outcome": {"status": "REJECTED", "reason": "Condition became irreversible after delays"}, "reward": 0.008999999999999996} {"seed": 562874771, "task": "acde_easy", "difficulty": "easy", "step": 3, "state": {"patient_condition": "critical", "remaining_time_minutes": 16.0, "failed_hospitals": ["H1"], "visited_hospitals": ["H4", "H1"], "ambulance_status": "rerouting"}, "action": {"hospital_id": "H4", "policy_score": 0.4523870351936169, "strategy": "risk-aware policy + anti-stupidity guard"}, "outcome": {"status": "ACCEPTED", "reason": "Emergency stabilization at last attempt"}, "reward": 0.6023999999999999} {"seed": 562874772, "task": "acde_medium", "difficulty": "medium", "step": 1, "state": {"patient_condition": "critical", "remaining_time_minutes": 14.0, "failed_hospitals": [], "visited_hospitals": [], "ambulance_status": "en_route"}, "action": {"hospital_id": "H5", "policy_score": 0.330475874967317, "strategy": "safe policy + critical triage"}, "outcome": {"status": "ACCEPTED", "reason": "Patient admitted and treatment began"}, "reward": 0.909} {"seed": 562874773, "task": "acde_hard", "difficulty": "hard", "step": 1, "state": {"patient_condition": "critical", "remaining_time_minutes": 11.0, "failed_hospitals": [], "visited_hospitals": [], "ambulance_status": "en_route"}, "action": {"hospital_id": "H6", "policy_score": 0.16730626096306447, "strategy": "safe policy"}, "outcome": {"status": "REJECTED", "reason": "Hospital cannot admit: Hospital overloaded"}, "reward": 0.001} {"seed": 562874773, "task": "acde_hard", "difficulty": "hard", "step": 2, "state": {"patient_condition": "critical", "remaining_time_minutes": 11.0, "failed_hospitals": ["H5"], "visited_hospitals": ["H5"], "ambulance_status": "rerouting"}, "action": {"hospital_id": "H1", "policy_score": 0.38920337366242297, "strategy": "risk-aware policy + anti-stupidity guard"}, "outcome": {"status": "PARTIAL", "reason": "Admitted with delays: prolonged transfer strain"}, "reward": 0.40800000000000014} {"seed": 562874773, "task": "acde_hard", "difficulty": "hard", "step": 3, "state": {"patient_condition": "critical", "remaining_time_minutes": 11.0, "failed_hospitals": ["H5"], "visited_hospitals": ["H5", "H1"], "ambulance_status": "in_transit"}, "action": {"hospital_id": "H4", "policy_score": 0.09872350410300806, "strategy": "balanced policy + critical triage"}, "outcome": {"status": "REJECTED", "reason": "Hospital cannot admit: ICU unavailable, No specialist available"}, "reward": 0.001} {"seed": 562874773, "task": "acde_hard", "difficulty": "hard", "step": 4, "state": {"patient_condition": "critical", "remaining_time_minutes": 11.0, "failed_hospitals": ["H5", "H4"], "visited_hospitals": ["H5", "H1", "H4"], "ambulance_status": "rerouting"}, "action": {"hospital_id": "H3", "policy_score": 0.23065044082853245, "strategy": "risk-aware policy"}, "outcome": {"status": "REJECTED", "reason": "Hospital cannot admit: No specialist available"}, "reward": 0.001} {"seed": 850880720, "task": "acde_easy", "difficulty": "easy", "step": 1, "state": {"patient_condition": "serious", "remaining_time_minutes": 18.0, "failed_hospitals": [], "visited_hospitals": [], "ambulance_status": "en_route"}, "action": {"hospital_id": "H3", "policy_score": 0.29399842964915673, "strategy": "safe policy"}, "outcome": {"status": "ACCEPTED", "reason": "Patient admitted and treatment began"}, "reward": 0.999} {"seed": 850880721, "task": "acde_medium", "difficulty": "medium", "step": 1, "state": {"patient_condition": "critical", "remaining_time_minutes": 14.0, "failed_hospitals": [], "visited_hospitals": [], "ambulance_status": "en_route"}, "action": {"hospital_id": "H2", "policy_score": 0.4445027887294011, "strategy": "safe policy + anti-stupidity guard"}, "outcome": {"status": "PARTIAL", "reason": "Admitted with delays: prolonged transfer strain, hospital busy but manageable"}, "reward": 0.13650000000000004} {"seed": 850880721, "task": "acde_medium", "difficulty": "medium", "step": 2, "state": {"patient_condition": "critical", "remaining_time_minutes": 14.0, "failed_hospitals": [], "visited_hospitals": ["H2"], "ambulance_status": "in_transit"}, "action": {"hospital_id": "H3", "policy_score": 0.4530366133689682, "strategy": "balanced policy + critical triage"}, "outcome": {"status": "PARTIAL", "reason": "Condition worsened but remains temporarily transferable"}, "reward": 0.17400000000000002} {"seed": 850880721, "task": "acde_medium", "difficulty": "medium", "step": 3, "state": {"patient_condition": "critical", "remaining_time_minutes": 14.0, "failed_hospitals": [], "visited_hospitals": ["H2", "H3"], "ambulance_status": "in_transit"}, "action": {"hospital_id": "H5", "policy_score": 0.36233580012122824, "strategy": "balanced policy + critical triage"}, "outcome": {"status": "REJECTED", "reason": "Doctor was reassigned to another emergency at arrival"}, "reward": 0.001} {"seed": 850880721, "task": "acde_medium", "difficulty": "medium", "step": 4, "state": {"patient_condition": "critical", "remaining_time_minutes": 14.0, "failed_hospitals": ["H1"], "visited_hospitals": ["H2", "H3", "H1"], "ambulance_status": "rerouting"}, "action": {"hospital_id": "H3", "policy_score": 0.2867098759261258, "strategy": "risk-aware policy + immediate-retry override"}, "outcome": {"status": "REJECTED", "reason": "Condition became non-transferable during delay; immediate critical care failed"}, "reward": 0.001} {"seed": 850880722, "task": "acde_hard", "difficulty": "hard", "step": 1, "state": {"patient_condition": "critical", "remaining_time_minutes": 12.0, "failed_hospitals": [], "visited_hospitals": [], "ambulance_status": "en_route"}, "action": {"hospital_id": "H3", "policy_score": 0.4706955388080195, "strategy": "safe policy + critical triage"}, "outcome": {"status": "REJECTED", "reason": "Hospital cannot admit: ICU unavailable"}, "reward": 0.001} {"seed": 850880722, "task": "acde_hard", "difficulty": "hard", "step": 2, "state": {"patient_condition": "critical", "remaining_time_minutes": 12.0, "failed_hospitals": ["H3"], "visited_hospitals": ["H3"], "ambulance_status": "rerouting"}, "action": {"hospital_id": "H5", "policy_score": 0.46941242001424005, "strategy": "risk-aware policy"}, "outcome": {"status": "ACCEPTED", "reason": "Condition stabilized after progressive treatment"}, "reward": 0.5820000000000001} {"seed": 600335717, "task": "acde_easy", "difficulty": "easy", "step": 1, "state": {"patient_condition": "critical", "remaining_time_minutes": 16.0, "failed_hospitals": [], "visited_hospitals": [], "ambulance_status": "en_route"}, "action": {"hospital_id": "H1", "policy_score": 0.3186401093335327, "strategy": "safe policy + critical triage + guided-exploration"}, "outcome": {"status": "REJECTED", "reason": "Condition became non-transferable during delay; immediate critical care failed"}, "reward": 0.139} {"seed": 600335718, "task": "acde_medium", "difficulty": "medium", "step": 1, "state": {"patient_condition": "serious", "remaining_time_minutes": 17.0, "failed_hospitals": [], "visited_hospitals": [], "ambulance_status": "en_route"}, "action": {"hospital_id": "H2", "policy_score": 0.4037159167006607, "strategy": "safe policy"}, "outcome": {"status": "REJECTED", "reason": "Hospital cannot admit: ICU unavailable"}, "reward": 0.109} {"seed": 600335718, "task": "acde_medium", "difficulty": "medium", "step": 2, "state": {"patient_condition": "serious", "remaining_time_minutes": 17.0, "failed_hospitals": ["H4"], "visited_hospitals": ["H4"], "ambulance_status": "rerouting"}, "action": {"hospital_id": "H4", "policy_score": 0.07313118251968914, "strategy": "risk-aware policy + anti-stupidity guard + immediate-retry override"}, "outcome": {"status": "ACCEPTED", "reason": "Patient stabilized after delayed admission"}, "reward": 0.516} {"seed": 600335719, "task": "acde_hard", "difficulty": "hard", "step": 1, "state": {"patient_condition": "critical", "remaining_time_minutes": 11.0, "failed_hospitals": [], "visited_hospitals": [], "ambulance_status": "en_route"}, "action": {"hospital_id": "H6", "policy_score": 0.3244976864117649, "strategy": "safe policy + critical triage + anti-stupidity guard"}, "outcome": {"status": "REJECTED", "reason": "Hidden mismatch at arrival (wrong risky guess). Rerouting required."}, "reward": 0.001} {"seed": 600335719, "task": "acde_hard", "difficulty": "hard", "step": 2, "state": {"patient_condition": "critical", "remaining_time_minutes": 11.0, "failed_hospitals": ["H6"], "visited_hospitals": ["H6"], "ambulance_status": "rerouting"}, "action": {"hospital_id": "H5", "policy_score": 0.2976383394515107, "strategy": "risk-aware policy"}, "outcome": {"status": "REJECTED", "reason": "Condition became non-transferable during delay; immediate critical care failed"}, "reward": 0.001} {"seed": 509813872, "task": "acde_easy", "difficulty": "easy", "step": 1, "state": {"patient_condition": "serious", "remaining_time_minutes": 20.0, "failed_hospitals": [], "visited_hospitals": [], "ambulance_status": "en_route"}, "action": {"hospital_id": "H3", "policy_score": 0.3729382136813107, "strategy": "safe policy"}, "outcome": {"status": "PARTIAL", "reason": "Early rejection mitigated by emergency field stabilization"}, "reward": 0.15500000000000003} {"seed": 509813872, "task": "acde_easy", "difficulty": "easy", "step": 2, "state": {"patient_condition": "serious", "remaining_time_minutes": 20.0, "failed_hospitals": [], "visited_hospitals": ["H3"], "ambulance_status": "in_transit"}, "action": {"hospital_id": "H1", "policy_score": 0.4212703202476848, "strategy": "balanced policy"}, "outcome": {"status": "REJECTED", "reason": "Hospital cannot admit: ICU unavailable, Hospital overloaded"}, "reward": 0.139} {"seed": 509813872, "task": "acde_easy", "difficulty": "easy", "step": 3, "state": {"patient_condition": "serious", "remaining_time_minutes": 20.0, "failed_hospitals": ["H1"], "visited_hospitals": ["H3", "H1"], "ambulance_status": "rerouting"}, "action": {"hospital_id": "H3", "policy_score": 0.4992501253122812, "strategy": "risk-aware policy + anti-stupidity guard"}, "outcome": {"status": "ACCEPTED", "reason": "Patient stabilized after delayed admission"}, "reward": 0.7160000000000001} {"seed": 509813873, "task": "acde_medium", "difficulty": "medium", "step": 1, "state": {"patient_condition": "critical", "remaining_time_minutes": 15.0, "failed_hospitals": [], "visited_hospitals": [], "ambulance_status": "en_route"}, "action": {"hospital_id": "H3", "policy_score": 0.4050067561693999, "strategy": "safe policy + critical triage"}, "outcome": {"status": "REJECTED", "reason": "Condition became non-transferable during delay; immediate critical care failed"}, "reward": 0.001} {"seed": 509813874, "task": "acde_hard", "difficulty": "hard", "step": 1, "state": {"patient_condition": "critical", "remaining_time_minutes": 11.0, "failed_hospitals": [], "visited_hospitals": [], "ambulance_status": "en_route"}, "action": {"hospital_id": "H1", "policy_score": 0.49875162318940436, "strategy": "safe policy + critical triage"}, "outcome": {"status": "REJECTED", "reason": "Hospital cannot admit: ICU unavailable, Hospital overloaded"}, "reward": 0.001} {"seed": 509813874, "task": "acde_hard", "difficulty": "hard", "step": 2, "state": {"patient_condition": "critical", "remaining_time_minutes": 11.0, "failed_hospitals": ["H1"], "visited_hospitals": ["H1"], "ambulance_status": "rerouting"}, "action": {"hospital_id": "H6", "policy_score": 0.49875162318940436, "strategy": "risk-aware policy + guided-exploration + anti-stupidity guard"}, "outcome": {"status": "REJECTED", "reason": "Hospital cannot admit: ICU unavailable"}, "reward": 0.039} {"seed": 509813874, "task": "acde_hard", "difficulty": "hard", "step": 3, "state": {"patient_condition": "critical", "remaining_time_minutes": 11.0, "failed_hospitals": ["H1", "H3"], "visited_hospitals": ["H1", "H3"], "ambulance_status": "rerouting"}, "action": {"hospital_id": "H4", "policy_score": 0.14285712242855392, "strategy": "risk-aware policy"}, "outcome": {"status": "REJECTED", "reason": "Hospital cannot admit: ICU unavailable"}, "reward": 0.001} {"seed": 509813874, "task": "acde_hard", "difficulty": "hard", "step": 4, "state": {"patient_condition": "critical", "remaining_time_minutes": 11.0, "failed_hospitals": ["H1", "H3", "H4"], "visited_hospitals": ["H1", "H3", "H4"], "ambulance_status": "rerouting"}, "action": {"hospital_id": "H6", "policy_score": 0.49875162318940436, "strategy": "risk-aware policy + anti-stupidity guard"}, "outcome": {"status": "REJECTED", "reason": "Hidden mismatch at arrival (wrong risky guess). Rerouting required."}, "reward": 0.001} {"seed": 579018919, "task": "acde_easy", "difficulty": "easy", "step": 1, "state": {"patient_condition": "serious", "remaining_time_minutes": 18.0, "failed_hospitals": [], "visited_hospitals": [], "ambulance_status": "en_route"}, "action": {"hospital_id": "H4", "policy_score": 0.32949151496142953, "strategy": "safe policy"}, "outcome": {"status": "PARTIAL", "reason": "Early rejection mitigated by emergency field stabilization"}, "reward": 0.30400000000000005} {"seed": 579018919, "task": "acde_easy", "difficulty": "easy", "step": 2, "state": {"patient_condition": "serious", "remaining_time_minutes": 18.0, "failed_hospitals": [], "visited_hospitals": ["H4"], "ambulance_status": "in_transit"}, "action": {"hospital_id": "H1", "policy_score": 0.34824268005046066, "strategy": "balanced policy + anti-stupidity guard"}, "outcome": {"status": "REJECTED", "reason": "Condition became irreversible after delays"}, "reward": 0.109} {"seed": 579018919, "task": "acde_easy", "difficulty": "easy", "step": 3, "state": {"patient_condition": "unstable", "remaining_time_minutes": 18.0, "failed_hospitals": ["H1"], "visited_hospitals": ["H4", "H1"], "ambulance_status": "rerouting"}, "action": {"hospital_id": "H4", "policy_score": 0.4992501253122812, "strategy": "risk-aware policy + anti-stupidity guard"}, "outcome": {"status": "ACCEPTED", "reason": "Condition stabilized after progressive treatment"}, "reward": 0.562} {"seed": 579018920, "task": "acde_medium", "difficulty": "medium", "step": 1, "state": {"patient_condition": "critical", "remaining_time_minutes": 15.0, "failed_hospitals": [], "visited_hospitals": [], "ambulance_status": "en_route"}, "action": {"hospital_id": "H3", "policy_score": 0.4843607591902248, "strategy": "safe policy + critical triage + anti-stupidity guard"}, "outcome": {"status": "REJECTED", "reason": "Hospital cannot admit: ICU unavailable"}, "reward": 0.001} {"seed": 579018920, "task": "acde_medium", "difficulty": "medium", "step": 2, "state": {"patient_condition": "critical", "remaining_time_minutes": 15.0, "failed_hospitals": ["H3"], "visited_hospitals": ["H3"], "ambulance_status": "rerouting"}, "action": {"hospital_id": "H5", "policy_score": 0.48373386963831955, "strategy": "risk-aware policy + anti-stupidity guard"}, "outcome": {"status": "PARTIAL", "reason": "Admitted with significant risk: No specialist available"}, "reward": 0.358} {"seed": 579018920, "task": "acde_medium", "difficulty": "medium", "step": 3, "state": {"patient_condition": "critical", "remaining_time_minutes": 15.0, "failed_hospitals": ["H3"], "visited_hospitals": ["H3", "H5"], "ambulance_status": "in_transit"}, "action": {"hospital_id": "H1", "policy_score": 0.16666663886108793, "strategy": "balanced policy"}, "outcome": {"status": "REJECTED", "reason": "Hospital cannot admit: ICU unavailable"}, "reward": 0.001} {"seed": 579018920, "task": "acde_medium", "difficulty": "medium", "step": 4, "state": {"patient_condition": "critical", "remaining_time_minutes": 15.0, "failed_hospitals": ["H3", "H1"], "visited_hospitals": ["H3", "H5", "H1"], "ambulance_status": "rerouting"}, "action": {"hospital_id": "H4", "policy_score": 0.16666663886108793, "strategy": "risk-aware policy"}, "outcome": {"status": "REJECTED", "reason": "Hidden mismatch at arrival (wrong risky guess). Rerouting required."}, "reward": 0.001} {"seed": 579018921, "task": "acde_hard", "difficulty": "hard", "step": 1, "state": {"patient_condition": "critical", "remaining_time_minutes": 11.0, "failed_hospitals": [], "visited_hospitals": [], "ambulance_status": "en_route"}, "action": {"hospital_id": "H1", "policy_score": 0.35191055672786264, "strategy": "safe policy + critical triage"}, "outcome": {"status": "REJECTED", "reason": "Hospital cannot admit: ICU unavailable"}, "reward": 0.001} {"seed": 579018921, "task": "acde_hard", "difficulty": "hard", "step": 2, "state": {"patient_condition": "critical", "remaining_time_minutes": 11.0, "failed_hospitals": ["H1"], "visited_hospitals": ["H1"], "ambulance_status": "rerouting"}, "action": {"hospital_id": "H6", "policy_score": 0.49875162318940436, "strategy": "risk-aware policy"}, "outcome": {"status": "REJECTED", "reason": "Hospital cannot admit: Hospital overloaded"}, "reward": 0.001} {"seed": 579018921, "task": "acde_hard", "difficulty": "hard", "step": 3, "state": {"patient_condition": "critical", "remaining_time_minutes": 11.0, "failed_hospitals": ["H1", "H6"], "visited_hospitals": ["H1", "H6"], "ambulance_status": "rerouting"}, "action": {"hospital_id": "H3", "policy_score": 0.14285712242855392, "strategy": "risk-aware policy"}, "outcome": {"status": "REJECTED", "reason": "Hospital cannot admit: Hospital overloaded"}, "reward": 0.001} {"seed": 579018921, "task": "acde_hard", "difficulty": "hard", "step": 4, "state": {"patient_condition": "critical", "remaining_time_minutes": 11.0, "failed_hospitals": ["H1", "H6", "H4"], "visited_hospitals": ["H1", "H6", "H4"], "ambulance_status": "rerouting"}, "action": {"hospital_id": "H5", "policy_score": 0.49875162318940436, "strategy": "risk-aware policy + anti-stupidity guard"}, "outcome": {"status": "PARTIAL", "reason": "Admitted with delays: prolonged transfer strain"}, "reward": 0.40800000000000014} {"seed": 468098215, "task": "acde_easy", "difficulty": "easy", "step": 1, "state": {"patient_condition": "serious", "remaining_time_minutes": 18.0, "failed_hospitals": [], "visited_hospitals": [], "ambulance_status": "en_route"}, "action": {"hospital_id": "H3", "policy_score": 0.3443315337257757, "strategy": "safe policy + anti-stupidity guard"}, "outcome": {"status": "PARTIAL", "reason": "Critical deterioration managed temporarily; reroute still needed"}, "reward": 0.334} {"seed": 468098215, "task": "acde_easy", "difficulty": "easy", "step": 2, "state": {"patient_condition": "stable", "remaining_time_minutes": 18.0, "failed_hospitals": [], "visited_hospitals": ["H3"], "ambulance_status": "in_transit"}, "action": {"hospital_id": "H4", "policy_score": 0.24369633883371342, "strategy": "balanced policy"}, "outcome": {"status": "REJECTED", "reason": "Emergency beds became unavailable during arrival"}, "reward": 0.001} {"seed": 468098215, "task": "acde_easy", "difficulty": "easy", "step": 3, "state": {"patient_condition": "stable", "remaining_time_minutes": 18.0, "failed_hospitals": ["H4"], "visited_hospitals": ["H3", "H4"], "ambulance_status": "rerouting"}, "action": {"hospital_id": "H1", "policy_score": 0.27278944968751606, "strategy": "risk-aware policy"}, "outcome": {"status": "REJECTED", "reason": "Condition became non-transferable during delay; immediate critical care failed"}, "reward": 0.139} {"seed": 468098216, "task": "acde_medium", "difficulty": "medium", "step": 1, "state": {"patient_condition": "serious", "remaining_time_minutes": 17.0, "failed_hospitals": [], "visited_hospitals": [], "ambulance_status": "en_route"}, "action": {"hospital_id": "H2", "policy_score": 0.4171322328020302, "strategy": "safe policy + guided-exploration"}, "outcome": {"status": "PARTIAL", "reason": "Initial triage completed; transfer monitoring still required"}, "reward": 0.37} {"seed": 468098216, "task": "acde_medium", "difficulty": "medium", "step": 2, "state": {"patient_condition": "serious", "remaining_time_minutes": 17.0, "failed_hospitals": [], "visited_hospitals": ["H2"], "ambulance_status": "in_transit"}, "action": {"hospital_id": "H3", "policy_score": 0.43825439745695755, "strategy": "balanced policy + anti-stupidity guard"}, "outcome": {"status": "ACCEPTED", "reason": "Patient stabilized after delayed admission"}, "reward": 0.8660000000000001} {"seed": 468098217, "task": "acde_hard", "difficulty": "hard", "step": 1, "state": {"patient_condition": "critical", "remaining_time_minutes": 12.0, "failed_hospitals": [], "visited_hospitals": [], "ambulance_status": "en_route"}, "action": {"hospital_id": "H2", "policy_score": 0.49964989496849055, "strategy": "safe policy + critical triage"}, "outcome": {"status": "REJECTED", "reason": "Hospital cannot admit: Hospital overloaded"}, "reward": 0.001} {"seed": 468098217, "task": "acde_hard", "difficulty": "hard", "step": 2, "state": {"patient_condition": "critical", "remaining_time_minutes": 12.0, "failed_hospitals": ["H2"], "visited_hospitals": ["H2"], "ambulance_status": "rerouting"}, "action": {"hospital_id": "H3", "policy_score": 0.29411764705882354, "strategy": "risk-aware policy"}, "outcome": {"status": "REJECTED", "reason": "Hidden mismatch at arrival (wrong risky guess). Rerouting required."}, "reward": 0.001} {"seed": 468098217, "task": "acde_hard", "difficulty": "hard", "step": 3, "state": {"patient_condition": "critical", "remaining_time_minutes": 12.0, "failed_hospitals": ["H2", "H3"], "visited_hospitals": ["H2", "H3"], "ambulance_status": "rerouting"}, "action": {"hospital_id": "H5", "policy_score": 0.039999999999999994, "strategy": "risk-aware policy"}, "outcome": {"status": "REJECTED", "reason": "Hidden mismatch at arrival (wrong risky guess). Rerouting required."}, "reward": 0.001} {"seed": 468098217, "task": "acde_hard", "difficulty": "hard", "step": 4, "state": {"patient_condition": "critical", "remaining_time_minutes": 12.0, "failed_hospitals": ["H2", "H3", "H1"], "visited_hospitals": ["H2", "H3", "H1"], "ambulance_status": "rerouting"}, "action": {"hospital_id": "H2", "policy_score": 0.29411764705882354, "strategy": "risk-aware policy + immediate-retry override"}, "outcome": {"status": "REJECTED", "reason": "Hospital cannot admit: ICU unavailable, No specialist available"}, "reward": 0.001} {"seed": 917229607, "task": "acde_easy", "difficulty": "easy", "step": 1, "state": {"patient_condition": "serious", "remaining_time_minutes": 18.0, "failed_hospitals": [], "visited_hospitals": [], "ambulance_status": "en_route"}, "action": {"hospital_id": "H1", "policy_score": 0.330194953786115, "strategy": "safe policy"}, "outcome": {"status": "ACCEPTED", "reason": "Patient stabilized after delayed admission"}, "reward": 0.8870000000000001} {"seed": 917229608, "task": "acde_medium", "difficulty": "medium", "step": 1, "state": {"patient_condition": "critical", "remaining_time_minutes": 14.0, "failed_hospitals": [], "visited_hospitals": [], "ambulance_status": "en_route"}, "action": {"hospital_id": "H5", "policy_score": 0.49333881522073353, "strategy": "safe policy + critical triage"}, "outcome": {"status": "PARTIAL", "reason": "Admitted with delays: patient worsened during transfer"}, "reward": 0.499} {"seed": 917229608, "task": "acde_medium", "difficulty": "medium", "step": 2, "state": {"patient_condition": "critical", "remaining_time_minutes": 14.0, "failed_hospitals": [], "visited_hospitals": ["H5"], "ambulance_status": "in_transit"}, "action": {"hospital_id": "H2", "policy_score": 0.39089664384926215, "strategy": "balanced policy + critical triage"}, "outcome": {"status": "REJECTED", "reason": "Hospital cannot admit: Hospital overloaded"}, "reward": 0.039} {"seed": 917229608, "task": "acde_medium", "difficulty": "medium", "step": 3, "state": {"patient_condition": "critical", "remaining_time_minutes": 14.0, "failed_hospitals": ["H2"], "visited_hospitals": ["H5", "H2"], "ambulance_status": "rerouting"}, "action": {"hospital_id": "H5", "policy_score": 0.47656977550308066, "strategy": "risk-aware policy + guided-exploration + anti-stupidity guard"}, "outcome": {"status": "ACCEPTED", "reason": "Patient stabilized after critical delay"}, "reward": 0.5336} {"seed": 917229609, "task": "acde_hard", "difficulty": "hard", "step": 1, "state": {"patient_condition": "critical", "remaining_time_minutes": 13.0, "failed_hospitals": [], "visited_hospitals": [], "ambulance_status": "en_route"}, "action": {"hospital_id": "H2", "policy_score": 0.49956106431243036, "strategy": "safe policy"}, "outcome": {"status": "REJECTED", "reason": "Hospital cannot admit: No specialist available, Hospital overloaded"}, "reward": 0.139} {"seed": 917229609, "task": "acde_hard", "difficulty": "hard", "step": 2, "state": {"patient_condition": "critical", "remaining_time_minutes": 13.0, "failed_hospitals": ["H5"], "visited_hospitals": ["H5"], "ambulance_status": "rerouting"}, "action": {"hospital_id": "H6", "policy_score": 0.025524969981599324, "strategy": "risk-aware policy + immediate-retry override"}, "outcome": {"status": "REJECTED", "reason": "Hospital cannot admit: No specialist available"}, "reward": 0.001} {"seed": 917229609, "task": "acde_hard", "difficulty": "hard", "step": 3, "state": {"patient_condition": "critical", "remaining_time_minutes": 13.0, "failed_hospitals": ["H5", "H6"], "visited_hospitals": ["H5", "H6"], "ambulance_status": "rerouting"}, "action": {"hospital_id": "H2", "policy_score": 0.4, "strategy": "risk-aware policy"}, "outcome": {"status": "PARTIAL", "reason": "Admitted with significant risk: ICU unavailable"}, "reward": 0.148} {"seed": 917229609, "task": "acde_hard", "difficulty": "hard", "step": 4, "state": {"patient_condition": "critical", "remaining_time_minutes": 13.0, "failed_hospitals": ["H5", "H6"], "visited_hospitals": ["H5", "H6", "H2"], "ambulance_status": "in_transit"}, "action": {"hospital_id": "H2", "policy_score": 0.4, "strategy": "balanced policy + critical triage + anti-stupidity guard"}, "outcome": {"status": "REJECTED", "reason": "Hospital cannot admit: Hospital overloaded"}, "reward": 0.001} {"seed": 259932461, "task": "acde_easy", "difficulty": "easy", "step": 1, "state": {"patient_condition": "critical", "remaining_time_minutes": 16.0, "failed_hospitals": [], "visited_hospitals": [], "ambulance_status": "en_route"}, "action": {"hospital_id": "H2", "policy_score": 0.332103, "strategy": "safe policy + critical triage"}, "outcome": {"status": "PARTIAL", "reason": "Admitted with delays: doctor delayed"}, "reward": 0.46} {"seed": 259932461, "task": "acde_easy", "difficulty": "easy", "step": 2, "state": {"patient_condition": "critical", "remaining_time_minutes": 16.0, "failed_hospitals": [], "visited_hospitals": ["H2"], "ambulance_status": "in_transit"}, "action": {"hospital_id": "H1", "policy_score": 0.494753, "strategy": "balanced policy + critical triage"}, "outcome": {"status": "PARTIAL", "reason": "Condition worsened but remains temporarily transferable"}, "reward": 0.285} {"seed": 259932461, "task": "acde_easy", "difficulty": "easy", "step": 3, "state": {"patient_condition": "unstable", "remaining_time_minutes": 16.0, "failed_hospitals": [], "visited_hospitals": ["H2", "H1"], "ambulance_status": "in_transit"}, "action": {"hospital_id": "H4", "policy_score": 0.394867, "strategy": "balanced policy + critical triage"}, "outcome": {"status": "REJECTED", "reason": "Condition became irreversible after delays"}, "reward": 0.03} {"seed": 977491037, "task": "acde_easy", "difficulty": "easy", "step": 1, "state": {"patient_condition": "critical", "remaining_time_minutes": 16.0, "failed_hospitals": [], "visited_hospitals": [], "ambulance_status": "en_route"}, "action": {"hospital_id": "H1", "policy_score": 0.412327, "strategy": "safe policy + guided-exploration"}, "outcome": {"status": "ACCEPTED", "reason": "Patient admitted and treatment began"}, "reward": 0.85} {"seed": 977491038, "task": "acde_medium", "difficulty": "medium", "step": 1, "state": {"patient_condition": "critical", "remaining_time_minutes": 14.0, "failed_hospitals": [], "visited_hospitals": [], "ambulance_status": "en_route"}, "action": {"hospital_id": "H5", "policy_score": 0.495455, "strategy": "safe policy + critical triage"}, "outcome": {"status": "PARTIAL", "reason": "Early rejection mitigated by emergency field stabilization"}, "reward": 0.255} {"seed": 977491038, "task": "acde_medium", "difficulty": "medium", "step": 2, "state": {"patient_condition": "critical", "remaining_time_minutes": 14.0, "failed_hospitals": [], "visited_hospitals": ["H5"], "ambulance_status": "in_transit"}, "action": {"hospital_id": "H2", "policy_score": 0.496739, "strategy": "balanced policy"}, "outcome": {"status": "ACCEPTED", "reason": "Condition stabilized after progressive treatment"}, "reward": 0.504} {"seed": 977491039, "task": "acde_hard", "difficulty": "hard", "step": 1, "state": {"patient_condition": "critical", "remaining_time_minutes": 12.0, "failed_hospitals": [], "visited_hospitals": [], "ambulance_status": "en_route"}, "action": {"hospital_id": "H6", "policy_score": 0.496489, "strategy": "safe policy + critical triage"}, "outcome": {"status": "PARTIAL", "reason": "Admitted with delays: prolonged transfer strain, doctor delayed"}, "reward": 0.2475} {"seed": 977491039, "task": "acde_hard", "difficulty": "hard", "step": 2, "state": {"patient_condition": "critical", "remaining_time_minutes": 12.0, "failed_hospitals": [], "visited_hospitals": ["H6"], "ambulance_status": "in_transit"}, "action": {"hospital_id": "H2", "policy_score": 0.294118, "strategy": "balanced policy"}, "outcome": {"status": "REJECTED", "reason": "Hidden mismatch at arrival (wrong risky guess). Rerouting required."}, "reward": 0.01} {"seed": 977491039, "task": "acde_hard", "difficulty": "hard", "step": 3, "state": {"patient_condition": "critical", "remaining_time_minutes": 12.0, "failed_hospitals": ["H5"], "visited_hospitals": ["H6", "H5"], "ambulance_status": "rerouting"}, "action": {"hospital_id": "H5", "policy_score": 0.027351, "strategy": "risk-aware policy + immediate-retry override"}, "outcome": {"status": "REJECTED", "reason": "Condition became irreversible after delays"}, "reward": 0.01} {"seed": 977491039, "task": "acde_hard", "difficulty": "hard", "step": 4, "state": {"patient_condition": "critical", "remaining_time_minutes": 12.0, "failed_hospitals": ["H5"], "visited_hospitals": ["H6", "H5"], "ambulance_status": "rerouting"}, "action": {"hospital_id": "H2", "policy_score": 0.294118, "strategy": "risk-aware policy"}, "outcome": {"status": "REJECTED", "reason": "Hidden mismatch at arrival (wrong risky guess). Rerouting required."}, "reward": 0.01}