run-output/plots/training_log.csv

round,avg_episode_reward,max_episode_reward,min_episode_reward,avg_grader,max_grader,n_training_samples,train_loss
1,3.904,4.514,3.287,0.6202,0.8268,101,2.6723
2,4.215,4.658,3.566,0.7325,0.8703,102,2.5934