Reinforcement Learning on Atari hard-exploration games (test)
435.56PPO Normalized Score (Mean)EIPO-RND
Evaluation results
| Method | Links | ||
|---|---|---|---|
| EIPO-RND2022.11 | 435.56 | — | |
| Ext-norm RND2022.11 | 427.08 | — | |
| RND2022.11 | 384.57 | — | |
| Decay-RND2022.11 | 383.83 | — | |
| Decoupled-RND2022.11 | 1.54 | — |