Reinforcement Learning on Atari solaris
12,326.7Max Agent ScoreAverage Human
Evaluation results
| Method | Links | |
|---|---|---|
| Average HumanPure-exploration regime=true2022.06 | 12,326.7 | |
| BYOL-ExplorePure-exploration regime=true, Episodes=10, Seeds=32022.06 | 4,298.2 | |
| RNDPure-exploration regime=true, Episodes=10, Seeds=32022.06 | 2,896.69 | |
| ICMPure-exploration regime=true, Episodes=10, Seeds=32022.06 | 2,851.86 |