Atari Games On Atari 2600 Assault
Metrics
Score
Results
Performance results of various models on this benchmark
Comparison Table
| Model Name | Score |
|---|---|
| the-reactor-a-fast-and-sample-efficient-actor | 8323.3 |
| deep-exploration-via-bootstrapped-dqn | 8047.1 |
| evolving-simple-programs-for-playing-atari | 890.4 |
| distributed-prioritized-experience-replay | 24559.4 |
| asynchronous-methods-for-deep-reinforcement | 14497.9 |
| deep-reinforcement-learning-with-double-q | 4280.4 |
| asynchronous-methods-for-deep-reinforcement | 5474.9 |
| agent57-outperforming-the-atari-human | 67212.67 |
| dueling-network-architectures-for-deep | 11477.0 |
| dueling-network-architectures-for-deep | 10950.6 |
| massively-parallel-methods-for-deep | 1195.8 |
| soft-actor-critic-for-discrete-action | 350 |
| increasing-the-action-gap-new-operators-for | 3661.51 |
| deep-reinforcement-learning-with-double-q | 6060.8 |
| deep-reinforcement-learning-with-double-q | 10950.6 |
| increasing-the-action-gap-new-operators-for | 3304.33 |
| a-distributional-perspective-on-reinforcement | 7203.0 |
| dueling-network-architectures-for-deep | 5393.2 |
| dueling-network-architectures-for-deep | 4621.0 |
| dueling-network-architectures-for-deep | 3994.8 |
| implicit-quantile-networks-for-distributional | 29091 |
| curl-contrastive-unsupervised-representations | 543.7 |
| prioritized-experience-replay | 7672.1 |
| mastering-atari-with-discrete-world-models-1 | 23625 |
| generalized-data-distribution-iteration | 97155 |
| prioritized-experience-replay | 6548.9 |
| generalized-data-distribution-iteration | 63876 |
| self-imitation-learning | 1812 |
| human-level-control-through-deep | 3359.0 |
| Model 30 | 537.0 |
| dna-proximal-policy-optimization-with-a-dual | 16293 |
| impala-scalable-distributed-deep-rl-with | 19148.47 |
| train-a-real-world-local-path-planner-in-one | 14372.8 |
| mastering-atari-go-chess-and-shogi-by | 143972.03 |
| recurrent-experience-replay-in-distributed | 108197.0 |
| the-arcade-learning-environment-an-evaluation | 628 |
| learning-values-across-many-orders-of | 9011.6 |
| asynchronous-methods-for-deep-reinforcement | 3746.1 |
| online-and-offline-reinforcement-learning-by | 33292.22 |
| the-arcade-learning-environment-an-evaluation | 1512.2 |
| deep-reinforcement-learning-with-double-q | 3489.3 |
| noisy-networks-for-exploration | 11231 |
| evolution-strategies-as-a-scalable | 1673.9 |
| distributional-reinforcement-learning-with-1 | 22012 |
| policy-optimization-with-penalized-point | 5400.13 |