benchmark_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,3,68.06916666666666,20,20,1.6666666666666667,1.3333333333333333,0.5555555555555556,0.0,70.25,0.5555555555555556,0.5555555555555556,0,,0.0
task1,RuleBasedAgent,3,250.92000000000002,20,20,3,0,1.0,1.0,74.16666666666667,1.0,1.0,0,,1.0
task1,RLAgent,3,215.845,20,20,3,0,1.0,1.0,62.666666666666664,1.0,1.0,0,,1.0
task1,TrainedQAgent,3,224.77499999999998,20,20,3,0,1.0,1.0,72.5,1.0,1.0,0,,1.0
task2,RandomAgent,3,46.04888888888889,24,24,2,2,0.5,0.0,35.5,0.5,0.5,0,,0.0
task2,RuleBasedAgent,3,129.65999999999997,24,24,1,3,0.25,0.0,20.0,0.25,0.25,0,,0.0
task2,RLAgent,3,254.79499999999996,24,24,2,2,0.5,1.0,50.583333333333336,0.5,0.5,0,,0.0
task2,TrainedQAgent,3,221.6283333333333,24,24,3,1,0.75,1.0,31.0,0.75,0.75,0,,1.0
task3,RandomAgent,3,-167.56847222222223,18,18,0,5,0.0,0.0,0.0,0.0,0.0,0,,0.0
task3,RuleBasedAgent,3,56.30999999999998,28,28,1,4,0.2,0.0,9.0,0.2,0.2,0,,0.0
task3,RLAgent,3,19.42958333333333,23,23,1.3333333333333333,3.6666666666666665,0.26666666666666666,0.0,80.83333333333333,0.26666666666666666,0.26666666666666666,0,,0.0
task3,TrainedQAgent,3,37.70999999999999,28,28,1,4,0.2,0.0,11.0,0.2,0.2,0,,0.0