You are using an older browser version. Please use a supported version for the best MSN experience.

AI learns to Speedrun QWOP (1:08) using Machine Learning

AI bot learns to play QWOP like a human and achieves a top 10 speedrun (1m 8s). Trained using Reinforcement Learning and Imitation Learning. Writeup: Github repo: Papers mentioned: - Sample Efficient Actor-Critic with Experience Replay - Deep Q-learning from Demonstrations Kurodo's channel: QWOP speedrun leaderboard:
image beaconimage beaconimage beacon