HyperAI초신경

Atari Games On Atari Games

평가 지표

Mean Human Normalized Score

평가 결과

이 벤치마크에서 각 모델의 성능 결과

비교 표
모델 이름Mean Human Normalized Score
model-based-reinforcement-learning-for-atari25.3%
never-give-up-learning-directed-exploration-13169.90%
first-return-then-explore4989.94%
impala-scalable-distributed-deep-rl-with957.34%
agent57-outperforming-the-atari-human4763.69%
off-policy-actor-critic-with-shared-11741.36%
generalized-data-distribution-iteration9620.33%
recurrent-experience-replay-in-distributed3374.31%
rainbow-combining-improvements-in-deep873.97%
mastering-atari-go-chess-and-shogi-by4996.20%
generalized-data-distribution-iteration7810.1%
mastering-atari-with-discrete-world-models-1631.17%