Reinforcement Learning on Atari Pitfall
6,463.7Max ScoreAverage Human
Evaluation results
| Method | Links | |
|---|---|---|
| Average HumanPure-exploration regime=true2022.06 | 6,463.7 | |
| BYOL-ExplorePure-exploration regime=true, Episodes=10, Seeds=32022.06 | 1,498.92 | |
| ICMPure-exploration regime=true, Episodes=10, Seeds=32022.06 | -7.53 | |
| RNDPure-exploration regime=true, Episodes=10, Seeds=32022.06 | -83.55 |