Spaces:
Running
Running
| { | |
| "model": "heuristic-baseline", | |
| "total_episodes": 30, | |
| "avg_score": 0.7942, | |
| "by_task": { | |
| "task1": { | |
| "episodes": 10, | |
| "avg_score": 0.8706 | |
| }, | |
| "task2": { | |
| "episodes": 10, | |
| "avg_score": 0.7475 | |
| }, | |
| "task3": { | |
| "episodes": 10, | |
| "avg_score": 0.7646 | |
| } | |
| }, | |
| "episodes": [ | |
| { | |
| "scenario_id": "SCN-TASK1-001", | |
| "task_type": "task1", | |
| "steps": 13, | |
| "score": 0.765, | |
| "total_reward": 10.71, | |
| "completion_rate": 0.8, | |
| "adversarial_detections": 0, | |
| "adversarial_poisonings": 0, | |
| "final_trust": { | |
| "S0": 0.473, | |
| "S1": 0.743, | |
| "S2": 0.5, | |
| "S3": 0.5, | |
| "S4": 0.5 | |
| } | |
| }, | |
| { | |
| "scenario_id": "SCN-TASK1-002", | |
| "task_type": "task1", | |
| "steps": 12, | |
| "score": 0.7962, | |
| "total_reward": 10.35, | |
| "completion_rate": 0.8, | |
| "adversarial_detections": 0, | |
| "adversarial_poisonings": 0, | |
| "final_trust": { | |
| "S0": 0.473, | |
| "S1": 0.888, | |
| "S2": 0.5, | |
| "S3": 0.5, | |
| "S4": 0.5 | |
| } | |
| }, | |
| { | |
| "scenario_id": "SCN-TASK1-003", | |
| "task_type": "task1", | |
| "steps": 11, | |
| "score": 0.885, | |
| "total_reward": 10.62, | |
| "completion_rate": 0.9, | |
| "adversarial_detections": 0, | |
| "adversarial_poisonings": 0, | |
| "final_trust": { | |
| "S0": 0.296, | |
| "S1": 0.296, | |
| "S2": 0.94, | |
| "S3": 0.5, | |
| "S4": 0.5 | |
| } | |
| }, | |
| { | |
| "scenario_id": "SCN-TASK1-004", | |
| "task_type": "task1", | |
| "steps": 8, | |
| "score": 0.99, | |
| "total_reward": 8.91, | |
| "completion_rate": 0.8, | |
| "adversarial_detections": 0, | |
| "adversarial_poisonings": 0, | |
| "final_trust": { | |
| "S0": 0.931, | |
| "S1": 0.5, | |
| "S2": 0.5, | |
| "S3": 0.5, | |
| "S4": 0.5 | |
| } | |
| }, | |
| { | |
| "scenario_id": "SCN-TASK1-005", | |
| "task_type": "task1", | |
| "steps": 11, | |
| "score": 0.9375, | |
| "total_reward": 11.25, | |
| "completion_rate": 1.0, | |
| "adversarial_detections": 0, | |
| "adversarial_poisonings": 0, | |
| "final_trust": { | |
| "S0": 0.86, | |
| "S1": 0.5, | |
| "S2": 0.5, | |
| "S3": 0.5, | |
| "S4": 0.5 | |
| } | |
| }, | |
| { | |
| "scenario_id": "SCN-TASK1-006", | |
| "task_type": "task1", | |
| "steps": 8, | |
| "score": 0.85, | |
| "total_reward": 7.65, | |
| "completion_rate": 0.6, | |
| "adversarial_detections": 0, | |
| "adversarial_poisonings": 0, | |
| "final_trust": { | |
| "S0": 0.71, | |
| "S1": 0.5, | |
| "S2": 0.5, | |
| "S3": 0.5, | |
| "S4": 0.5 | |
| } | |
| }, | |
| { | |
| "scenario_id": "SCN-TASK1-007", | |
| "task_type": "task1", | |
| "steps": 10, | |
| "score": 0.99, | |
| "total_reward": 10.89, | |
| "completion_rate": 1.0, | |
| "adversarial_detections": 0, | |
| "adversarial_poisonings": 0, | |
| "final_trust": { | |
| "S0": 0.943, | |
| "S1": 0.5, | |
| "S2": 0.5, | |
| "S3": 0.5, | |
| "S4": 0.5 | |
| } | |
| }, | |
| { | |
| "scenario_id": "SCN-TASK1-008", | |
| "task_type": "task1", | |
| "steps": 11, | |
| "score": 0.8325, | |
| "total_reward": 9.99, | |
| "completion_rate": 0.8, | |
| "adversarial_detections": 0, | |
| "adversarial_poisonings": 0, | |
| "final_trust": { | |
| "S0": 0.482, | |
| "S1": 0.9, | |
| "S2": 0.5, | |
| "S3": 0.5, | |
| "S4": 0.5 | |
| } | |
| }, | |
| { | |
| "scenario_id": "SCN-TASK1-009", | |
| "task_type": "task1", | |
| "steps": 9, | |
| "score": 0.864, | |
| "total_reward": 8.64, | |
| "completion_rate": 0.7, | |
| "adversarial_detections": 0, | |
| "adversarial_poisonings": 0, | |
| "final_trust": { | |
| "S0": 0.492, | |
| "S1": 0.801, | |
| "S2": 0.5, | |
| "S3": 0.5, | |
| "S4": 0.5 | |
| } | |
| }, | |
| { | |
| "scenario_id": "SCN-TASK1-010", | |
| "task_type": "task1", | |
| "steps": 12, | |
| "score": 0.7962, | |
| "total_reward": 10.35, | |
| "completion_rate": 0.8, | |
| "adversarial_detections": 0, | |
| "adversarial_poisonings": 0, | |
| "final_trust": { | |
| "S0": 0.494, | |
| "S1": 0.885, | |
| "S2": 0.5, | |
| "S3": 0.5, | |
| "S4": 0.5 | |
| } | |
| }, | |
| { | |
| "scenario_id": "SCN-TASK2-001", | |
| "task_type": "task2", | |
| "steps": 19, | |
| "score": 0.6054, | |
| "total_reward": 12.1087, | |
| "completion_rate": 0.8, | |
| "adversarial_detections": 0, | |
| "adversarial_poisonings": 0, | |
| "final_trust": { | |
| "S0": 0.476, | |
| "S1": 0.26, | |
| "S2": 0.717, | |
| "S3": 0.5, | |
| "S4": 0.5 | |
| } | |
| }, | |
| { | |
| "scenario_id": "SCN-TASK2-002", | |
| "task_type": "task2", | |
| "steps": 17, | |
| "score": 0.7762, | |
| "total_reward": 13.9711, | |
| "completion_rate": 0.933, | |
| "adversarial_detections": 0, | |
| "adversarial_poisonings": 0, | |
| "final_trust": { | |
| "S0": 0.478, | |
| "S1": 0.958, | |
| "S2": 0.5, | |
| "S3": 0.5, | |
| "S4": 0.5 | |
| } | |
| }, | |
| { | |
| "scenario_id": "SCN-TASK2-003", | |
| "task_type": "task2", | |
| "steps": 17, | |
| "score": 0.7377, | |
| "total_reward": 13.2781, | |
| "completion_rate": 0.867, | |
| "adversarial_detections": 0, | |
| "adversarial_poisonings": 0, | |
| "final_trust": { | |
| "S0": 0.289, | |
| "S1": 0.289, | |
| "S2": 0.818, | |
| "S3": 0.5, | |
| "S4": 0.5 | |
| } | |
| }, | |
| { | |
| "scenario_id": "SCN-TASK2-004", | |
| "task_type": "task2", | |
| "steps": 15, | |
| "score": 0.7783, | |
| "total_reward": 12.4521, | |
| "completion_rate": 0.933, | |
| "adversarial_detections": 0, | |
| "adversarial_poisonings": 0, | |
| "final_trust": { | |
| "S0": 0.9, | |
| "S1": 0.5, | |
| "S2": 0.5, | |
| "S3": 0.5, | |
| "S4": 0.5 | |
| } | |
| }, | |
| { | |
| "scenario_id": "SCN-TASK2-005", | |
| "task_type": "task2", | |
| "steps": 17, | |
| "score": 0.8174, | |
| "total_reward": 14.7129, | |
| "completion_rate": 1.0, | |
| "adversarial_detections": 0, | |
| "adversarial_poisonings": 0, | |
| "final_trust": { | |
| "S0": 0.849, | |
| "S1": 0.5, | |
| "S2": 0.5, | |
| "S3": 0.5, | |
| "S4": 0.5 | |
| } | |
| }, | |
| { | |
| "scenario_id": "SCN-TASK2-006", | |
| "task_type": "task2", | |
| "steps": 15, | |
| "score": 0.6476, | |
| "total_reward": 10.3617, | |
| "completion_rate": 0.733, | |
| "adversarial_detections": 0, | |
| "adversarial_poisonings": 0, | |
| "final_trust": { | |
| "S0": 0.708, | |
| "S1": 0.5, | |
| "S2": 0.5, | |
| "S3": 0.5, | |
| "S4": 0.5 | |
| } | |
| }, | |
| { | |
| "scenario_id": "SCN-TASK2-007", | |
| "task_type": "task2", | |
| "steps": 15, | |
| "score": 0.8967, | |
| "total_reward": 14.3478, | |
| "completion_rate": 1.0, | |
| "adversarial_detections": 0, | |
| "adversarial_poisonings": 0, | |
| "final_trust": { | |
| "S0": 0.967, | |
| "S1": 0.5, | |
| "S2": 0.5, | |
| "S3": 0.5, | |
| "S4": 0.5 | |
| } | |
| }, | |
| { | |
| "scenario_id": "SCN-TASK2-008", | |
| "task_type": "task2", | |
| "steps": 17, | |
| "score": 0.7442, | |
| "total_reward": 13.3953, | |
| "completion_rate": 0.933, | |
| "adversarial_detections": 0, | |
| "adversarial_poisonings": 0, | |
| "final_trust": { | |
| "S0": 0.49, | |
| "S1": 0.959, | |
| "S2": 0.5, | |
| "S3": 0.5, | |
| "S4": 0.5 | |
| } | |
| }, | |
| { | |
| "scenario_id": "SCN-TASK2-009", | |
| "task_type": "task2", | |
| "steps": 16, | |
| "score": 0.7525, | |
| "total_reward": 12.792, | |
| "completion_rate": 0.933, | |
| "adversarial_detections": 0, | |
| "adversarial_poisonings": 0, | |
| "final_trust": { | |
| "S0": 0.492, | |
| "S1": 0.906, | |
| "S2": 0.5, | |
| "S3": 0.5, | |
| "S4": 0.5 | |
| } | |
| }, | |
| { | |
| "scenario_id": "SCN-TASK2-010", | |
| "task_type": "task2", | |
| "steps": 18, | |
| "score": 0.7191, | |
| "total_reward": 13.6622, | |
| "completion_rate": 0.933, | |
| "adversarial_detections": 0, | |
| "adversarial_poisonings": 0, | |
| "final_trust": { | |
| "S0": 0.474, | |
| "S1": 0.955, | |
| "S2": 0.5, | |
| "S3": 0.5, | |
| "S4": 0.5 | |
| } | |
| }, | |
| { | |
| "scenario_id": "SCN-TASK3-001", | |
| "task_type": "task3", | |
| "steps": 25, | |
| "score": 0.7354, | |
| "total_reward": 19.1204, | |
| "completion_rate": 0.85, | |
| "adversarial_detections": 0, | |
| "adversarial_poisonings": 0, | |
| "final_trust": { | |
| "S0": 0.456, | |
| "S1": 0.258, | |
| "S2": 0.76, | |
| "S3": 0.5, | |
| "S4": 0.5 | |
| } | |
| }, | |
| { | |
| "scenario_id": "SCN-TASK3-002", | |
| "task_type": "task3", | |
| "steps": 25, | |
| "score": 0.7054, | |
| "total_reward": 18.341, | |
| "completion_rate": 0.85, | |
| "adversarial_detections": 3, | |
| "adversarial_poisonings": 5, | |
| "final_trust": { | |
| "S0": 0.458, | |
| "S1": 0.473, | |
| "S2": 0.868, | |
| "S3": 0.5, | |
| "S4": 0.5 | |
| } | |
| }, | |
| { | |
| "scenario_id": "SCN-TASK3-003", | |
| "task_type": "task3", | |
| "steps": 19, | |
| "score": 0.6438, | |
| "total_reward": 12.8767, | |
| "completion_rate": 0.6, | |
| "adversarial_detections": 0, | |
| "adversarial_poisonings": 5, | |
| "final_trust": { | |
| "S0": 0.299, | |
| "S1": 0.299, | |
| "S2": 0.633, | |
| "S3": 0.5, | |
| "S4": 0.5 | |
| } | |
| }, | |
| { | |
| "scenario_id": "SCN-TASK3-004", | |
| "task_type": "task3", | |
| "steps": 21, | |
| "score": 0.8954, | |
| "total_reward": 19.6992, | |
| "completion_rate": 1.0, | |
| "adversarial_detections": 0, | |
| "adversarial_poisonings": 0, | |
| "final_trust": { | |
| "S0": 0.93, | |
| "S1": 0.5, | |
| "S2": 0.5, | |
| "S3": 0.5, | |
| "S4": 0.5 | |
| } | |
| }, | |
| { | |
| "scenario_id": "SCN-TASK3-005", | |
| "task_type": "task3", | |
| "steps": 24, | |
| "score": 0.7134, | |
| "total_reward": 17.8339, | |
| "completion_rate": 0.85, | |
| "adversarial_detections": 3, | |
| "adversarial_poisonings": 6, | |
| "final_trust": { | |
| "S0": 0.491, | |
| "S1": 0.797, | |
| "S2": 0.5, | |
| "S3": 0.5, | |
| "S4": 0.5 | |
| } | |
| }, | |
| { | |
| "scenario_id": "SCN-TASK3-006", | |
| "task_type": "task3", | |
| "steps": 23, | |
| "score": 0.7857, | |
| "total_reward": 18.8578, | |
| "completion_rate": 0.9, | |
| "adversarial_detections": 0, | |
| "adversarial_poisonings": 0, | |
| "final_trust": { | |
| "S0": 0.774, | |
| "S1": 0.5, | |
| "S2": 0.5, | |
| "S3": 0.5, | |
| "S4": 0.5 | |
| } | |
| }, | |
| { | |
| "scenario_id": "SCN-TASK3-007", | |
| "task_type": "task3", | |
| "steps": 24, | |
| "score": 0.7045, | |
| "total_reward": 17.6133, | |
| "completion_rate": 0.85, | |
| "adversarial_detections": 3, | |
| "adversarial_poisonings": 7, | |
| "final_trust": { | |
| "S0": 0.498, | |
| "S1": 0.5, | |
| "S2": 0.5, | |
| "S3": 0.5, | |
| "S4": 0.5 | |
| } | |
| }, | |
| { | |
| "scenario_id": "SCN-TASK3-008", | |
| "task_type": "task3", | |
| "steps": 24, | |
| "score": 0.8057, | |
| "total_reward": 20.1435, | |
| "completion_rate": 0.95, | |
| "adversarial_detections": 0, | |
| "adversarial_poisonings": 0, | |
| "final_trust": { | |
| "S0": 0.479, | |
| "S1": 0.856, | |
| "S2": 0.5, | |
| "S3": 0.5, | |
| "S4": 0.5 | |
| } | |
| }, | |
| { | |
| "scenario_id": "SCN-TASK3-009", | |
| "task_type": "task3", | |
| "steps": 23, | |
| "score": 0.8456, | |
| "total_reward": 20.2932, | |
| "completion_rate": 1.0, | |
| "adversarial_detections": 0, | |
| "adversarial_poisonings": 0, | |
| "final_trust": { | |
| "S0": 0.488, | |
| "S1": 0.891, | |
| "S2": 0.5, | |
| "S3": 0.5, | |
| "S4": 0.5 | |
| } | |
| }, | |
| { | |
| "scenario_id": "SCN-TASK3-010", | |
| "task_type": "task3", | |
| "steps": 24, | |
| "score": 0.8106, | |
| "total_reward": 20.2645, | |
| "completion_rate": 0.95, | |
| "adversarial_detections": 0, | |
| "adversarial_poisonings": 0, | |
| "final_trust": { | |
| "S0": 0.473, | |
| "S1": 0.91, | |
| "S2": 0.5, | |
| "S3": 0.5, | |
| "S4": 0.5 | |
| } | |
| } | |
| ] | |
| } |