Atari Games On Atari 2600 Time Pilot
Metrics
Score
Results
Performance results of various models on this benchmark
Comparison Table
| Model Name | Score |
|---|---|
| increasing-the-action-gap-new-operators-for | 8969.12 |
| asynchronous-methods-for-deep-reinforcement | 12679.0 |
| the-arcade-learning-environment-an-evaluation | 3741.2 |
| generalized-data-distribution-iteration | 216770 |
| noisy-networks-for-exploration | 17301 |
| dueling-network-architectures-for-deep | 8339.0 |
| dueling-network-architectures-for-deep | 11666.0 |
| policy-optimization-with-penalized-point | 3770.33 |
| human-level-control-through-deep | 5947.0 |
| distributional-reinforcement-learning-with-1 | 10345 |
| dna-proximal-policy-optimization-with-a-dual | 12774 |
| recurrent-rational-networks | 17632 |
| mastering-atari-go-chess-and-shogi-by | 476763.90 |
| the-arcade-learning-environment-an-evaluation | 63854.5 |
| evolution-strategies-as-a-scalable | 4970.0 |
| playing-atari-with-six-neurons | 4600 |
| deep-exploration-via-bootstrapped-dqn | 9079.4 |
| recurrent-experience-replay-in-distributed | 445377.3 |
| learning-values-across-many-orders-of | 4870.0 |
| evolving-simple-programs-for-playing-atari | 12040 |
| prioritized-experience-replay | 5963.0 |
| dueling-network-architectures-for-deep | 7553.0 |
| dueling-network-architectures-for-deep | 6601.0 |
| online-and-offline-reinforcement-learning-by | 424011.16 |
| prioritized-experience-replay | 9197.0 |
| gdi-rethinking-what-makes-reinforcement | 216770 |
| mastering-atari-with-discrete-world-models-1 | 37945 |
| Model 28 | 24.9 |
| distributed-prioritized-experience-replay | 87085 |
| agent57-outperforming-the-atari-human | 405425.31 |
| implicit-quantile-networks-for-distributional | 12236 |
| deep-reinforcement-learning-with-double-q | 4871.0 |
| deep-reinforcement-learning-with-double-q | 4870.0 |
| massively-parallel-methods-for-deep | 8267.8 |
| self-imitation-learning | 10811.7 |
| recurrent-rational-networks | 13261 |
| deep-reinforcement-learning-with-double-q | 6608.0 |
| deep-reinforcement-learning-with-double-q | 4786.0 |
| asynchronous-methods-for-deep-reinforcement | 27202.0 |
| a-distributional-perspective-on-reinforcement | 8329.0 |
| train-a-real-world-local-path-planner-in-one | 12071 |
| impala-scalable-distributed-deep-rl-with | 48481.50 |
| asynchronous-methods-for-deep-reinforcement | 5825.0 |
| generalized-data-distribution-iteration | 450810 |