Atari Games On Atari 2600 Pitfall
Metrics
Score
Results
Performance results of various models on this benchmark
Comparison Table
| Model Name | Score |
|---|---|
| noisy-networks-for-exploration | 0 |
| first-return-then-explore | 6954 |
| policy-optimization-with-penalized-point | 0 |
| distributional-reinforcement-learning-with-1 | 0 |
| implicit-quantile-networks-for-distributional | 0 |
| dna-proximal-policy-optimization-with-a-dual | 0 |
| increasing-the-action-gap-new-operators-for | 0 |
| online-and-offline-reinforcement-learning-by | 0 |
| exploration-by-self-supervised-exploitation | 0 |
| mastering-atari-go-chess-and-shogi-by | 0.00 |
| exploration-by-self-supervised-exploitation | 0 |
| mastering-atari-with-discrete-world-models-1 | 0 |
| evolving-simple-programs-for-playing-atari | 0 |
| generalized-data-distribution-iteration | -4.345 |
| distributed-prioritized-experience-replay | -0.6 |
| go-explore-a-new-approach-for-hard | 102571 |
| train-a-real-world-local-path-planner-in-one | 0 |
| impala-scalable-distributed-deep-rl-with | -1.66 |
| recurrent-experience-replay-in-distributed | 0.0 |
| exploration-by-random-network-distillation | -3 |
| gdi-rethinking-what-makes-reinforcement | 0 |
| agent57-outperforming-the-atari-human | 18756.01 |
| generalized-data-distribution-iteration | 0 |