search

Kaixhin / Rainbow

Rainbow: Combining Improvements in Deep Reinforcement Learning
MIT License
1.59k stars 284 forks source link

Breakout #19

Closed Kaixhin closed 6 years ago

Kaixhin commented 6 years ago

Need to work out why Breakout fails to learn. After checking with Charles Beattie, DeepMind does not use OpenAI's FireResetEnv environment wrapper.

Kaixhin commented 6 years ago

Breakout works fine now - will upload trained model and training curves once finished.