Atari Games On Atari 2600 Solaris
Metriken
Score
Ergebnisse
Leistungsergebnisse verschiedener Modelle zu diesem Benchmark
Vergleichstabelle
| Modellname | Score |
|---|---|
| evolving-simple-programs-for-playing-atari | 8324 |
| recurrent-experience-replay-in-distributed | 3787.2 |
| online-and-offline-reinforcement-learning-by | 5132.95 |
| dna-proximal-policy-optimization-with-a-dual | 2225 |
| noisy-networks-for-exploration | 6522 |
| exploration-by-self-supervised-exploitation | 11865 |
| generalized-data-distribution-iteration | 9105 |
| mastering-atari-go-chess-and-shogi-by | 56.62 |
| impala-scalable-distributed-deep-rl-with | 2365.00 |
| generalized-data-distribution-iteration | 11074 |
| gdi-rethinking-what-makes-reinforcement | 11074 |
| exploration-by-random-network-distillation | 3282 |
| increasing-the-action-gap-new-operators-for | 4785.16 |
| exploration-by-self-supervised-exploitation | 12460 |
| distributed-prioritized-experience-replay | 2892.9 |
| implicit-quantile-networks-for-distributional | 8007 |
| train-a-real-world-local-path-planner-in-one | 3506.8 |
| mastering-atari-with-discrete-world-models-1 | 922 |
| exploration-by-self-supervised-exploitation | 11582 |
| first-return-then-explore | 19671 |
| count-based-exploration-with-the-successor | 2244.6 |
| distributional-reinforcement-learning-with-1 | 6740 |
| agent57-outperforming-the-atari-human | 44199.93 |