playing-mario-with-deep-reinforcement-learning
playing-mario-with-deep-reinforcement-learning copied to clipboard
Published
20 hours ago •
Kautenja
Kautenja
Broken Prioritized Experience Replay
results on Pong seem to indicate that the experience replay functionality is not working correctly. Performance is terrible, and the agent is far worse than its vanilla alternative. The paper introducing this technique will need reviewed to locate the source of the learning error. A code review is necessary to understand performance limitations and improve the runtime.
https://github.com/openai/baselines/blob/master/baselines/deepq/replay_buffer.py