Atari Games On Atari 2600 Asteroids
Metrics
Score
Results
Performance results of various models on this benchmark
Comparison Table
| Model Name | Score |
|---|---|
| prioritized-experience-replay | 2654.3 |
| mastering-atari-with-discrete-world-models-1 | 41526 |
| dueling-network-architectures-for-deep | 1192.7 |
| a-distributional-perspective-on-reinforcement | 1516.0 |
| generalized-data-distribution-iteration | 760005 |
| massively-parallel-methods-for-deep | 933.6 |
| dueling-network-architectures-for-deep | 2837.7 |
| generalized-data-distribution-iteration | 751970 |
| prioritized-experience-replay | 1745.1 |
| the-reactor-a-fast-and-sample-efficient-actor | 3726.1 |
| Model 11 | 89.0 |
| impala-scalable-distributed-deep-rl-with | 108590.05 |
| dna-proximal-policy-optimization-with-a-dual | 165973 |
| deep-reinforcement-learning-with-double-q | 1364.5 |
| policy-optimization-with-penalized-point | 2488.1 |
| evolution-strategies-as-a-scalable | 1562.0 |
| distributional-reinforcement-learning-with-1 | 4226 |
| increasing-the-action-gap-new-operators-for | 1924.42 |
| deep-reinforcement-learning-with-double-q | 1021.9 |
| distributed-prioritized-experience-replay | 155495.1 |
| self-imitation-learning | 2259.4 |
| deep-reinforcement-learning-with-double-q | 1458.7 |
| noisy-networks-for-exploration | 86700 |
| mastering-atari-go-chess-and-shogi-by | 678558.64 |
| human-level-control-through-deep | 1629.0 |
| dueling-network-architectures-for-deep | 2035.4 |
| learning-values-across-many-orders-of | 2869.3 |
| agent57-outperforming-the-atari-human | 150854.61 |
| asynchronous-methods-for-deep-reinforcement | 5093.1 |
| deep-reinforcement-learning-with-double-q | 1193.2 |
| evolving-simple-programs-for-playing-atari | 9412 |
| asynchronous-methods-for-deep-reinforcement | 3009.4 |
| dueling-network-architectures-for-deep | 734.7 |
| asynchronous-methods-for-deep-reinforcement | 4474.5 |
| fully-parameterized-quantile-function-for | 4553.0 |
| increasing-the-action-gap-new-operators-for | 1673.52 |
| online-and-offline-reinforcement-learning-by | 476412 |
| recurrent-experience-replay-in-distributed | 357867.7 |
| implicit-quantile-networks-for-distributional | 2898 |
| train-a-real-world-local-path-planner-in-one | 1984.5 |
| the-arcade-learning-environment-an-evaluation | 4660.6 |
| deep-exploration-via-bootstrapped-dqn | 1032 |
| the-arcade-learning-environment-an-evaluation | 907.3 |