benchmark_test_final.csv

task,agent_name,episodes,avg_total_reward,avg_episode_length,avg_steps,avg_survivors,avg_deaths,survival_rate,critical_survival_rate,avg_health_alive,stabilization_rate,avg_stabilization_rate,invalid_action_count,avg_invalid_action_count,success_rate
task1,RandomAgent,2,60.83375,20,20,1.5,1.5,0.5,0.0,76.75,0.5,0.5,0,,0.0
task1,RuleBasedAgent,2,250.92000000000002,20,20,3,0,1.0,1.0,74.16666666666667,1.0,1.0,0,,1.0
task1,RLAgent,2,215.845,20,20,3,0,1.0,1.0,62.666666666666664,1.0,1.0,0,,1.0
task1,TrainedQAgent,2,224.77499999999998,20,20,3,0,1.0,1.0,72.5,1.0,1.0,0,,1.0
task2,RandomAgent,2,35.79416666666667,24,24,2,2,0.5,0.0,27.75,0.5,0.5,0,,0.0
task2,RuleBasedAgent,2,129.65999999999997,24,24,1,3,0.25,0.0,20.0,0.25,0.25,0,,0.0
task2,RLAgent,2,258.625,24,24,2,2,0.5,1.0,51.75,0.5,0.5,0,,0.0
task2,TrainedQAgent,2,221.6283333333333,24,24,3,1,0.75,1.0,31.0,0.75,0.75,0,,1.0
task3,RandomAgent,2,-161.50520833333334,20,20,0,5,0.0,0.0,0.0,0.0,0.0,0,,0.0
task3,RuleBasedAgent,2,56.30999999999998,28,28,1,4,0.2,0.0,9.0,0.2,0.2,0,,0.0
task3,RLAgent,2,57.79854166666666,28,28,1.5,3.5,0.30000000000000004,0.0,71.25,0.30000000000000004,0.30000000000000004,0,,0.0
task3,TrainedQAgent,2,37.70999999999999,28,28,1,4,0.2,0.0,11.0,0.2,0.2,0,,0.0