bad_reward_shaping_version is the version that use a bad rewarding function.
ALSF_submission_final_code is the final version of the code file that used to run all experiments.
experiments folder includes four experiment folder: each folder includes a video and five graphs.
best_performance_video is in the experiment_1 folder
experiment_1: PPO + vector normalization + reward shaping functions + action clipping experiment 2: PPO + vector normalization + action clipping experiment 3: PPO + vector normalization experiment 4: basic PPO