task3_after_train.csv

agent_name,avg_total_reward,critical_survival_rate,success_rate,ventilator_utilization,invalid_action_count,meets_targets,milestone_a,milestone_b,milestone_c,failure_modes,failure_reason_counts,checkpoint_status,checkpoint_warning
RandomAgent,-391.4277,0.0000,0.0000,0.0000,0,False,False,False,False,critical_survival_too_low;success_rate_too_low;reward_not_above_rule_based;ventilator_use_too_low;failure_reasons=failed_both:30,failed_both:30,,
RuleBasedAgent,-108.8233,0.0000,0.0000,0.0000,0,False,False,False,False,critical_survival_too_low;success_rate_too_low;reward_not_above_rule_based;ventilator_use_too_low;failure_reasons=failed_survival_threshold:30,failed_survival_threshold:30,,
LLMAgent,-151.8700,0.0000,0.0000,0.1786,0,False,False,False,False,critical_survival_too_low;success_rate_too_low;reward_not_above_rule_based;ventilator_use_too_low;failure_reasons=failed_both:30,failed_both:30,,
TrainedQAgent,-221.1278,0.0167,0.0000,0.6434,0,False,False,False,False,critical_survival_too_low;success_rate_too_low;reward_not_above_rule_based;failure_reasons=failed_survival_threshold:19;failed_both:11,failed_both:11;failed_survival_threshold:19,fresh,
RLAgent,-66.8127,0.1167,0.0000,0.5940,0,False,False,False,False,critical_survival_too_low;success_rate_too_low;failure_reasons=failed_survival_threshold:26;failed_both:4,failed_both:4;failed_survival_threshold:26,fresh,