Atari Games On Atari 2600 Amidar
Metrics
Score
Results
Performance results of various models on this benchmark
Comparison Table
| Model Name | Score |
|---|---|
| value-prediction-network | 641 |
| recurrent-experience-replay-in-distributed | 29321.4 |
| asynchronous-methods-for-deep-reinforcement | 283.9 |
| generalized-data-distribution-iteration | 1442 |
| curl-contrastive-unsupervised-representations | 232.3 |
| mastering-atari-with-discrete-world-models-1 | 2577 |
| human-level-control-through-deep | 739.5 |
| distributed-prioritized-experience-replay | 8659.2 |
| dueling-network-architectures-for-deep | 238.4 |
| deep-reinforcement-learning-with-double-q | 238.4 |
| policy-optimization-with-penalized-point | 729.15 |
| deep-reinforcement-learning-with-double-q | 978.0 |
| improving-computational-efficiency-in-visual | 250.5 |
| self-imitation-learning | 1362 |
| the-reactor-a-fast-and-sample-efficient-actor | 1015.8 |
| a-distributional-perspective-on-reinforcement | 1735.0 |
| train-a-real-world-local-path-planner-in-one | 2232.3 |
| agent57-outperforming-the-atari-human | 29660.08 |
| distributional-reinforcement-learning-with-1 | 1641 |
| increasing-the-action-gap-new-operators-for | 1451.65 |
| increasing-the-action-gap-new-operators-for | 1557.43 |
| dueling-network-architectures-for-deep | 1793.3 |
| the-arcade-learning-environment-an-evaluation | 180.3 |
| deep-reinforcement-learning-with-double-q | 169.1 |
| soft-actor-critic-for-discrete-action | 7.9 |
| implicit-quantile-networks-for-distributional | 2946 |
| the-arcade-learning-environment-an-evaluation | 103.4 |
| deep-reinforcement-learning-with-double-q | 178.4 |
| dueling-network-architectures-for-deep | 172.7 |
| dueling-network-architectures-for-deep | 2354.5 |
| massively-parallel-methods-for-deep | 189.2 |
| noisy-networks-for-exploration | 3537 |
| dna-proximal-policy-optimization-with-a-dual | 1025 |
| impala-scalable-distributed-deep-rl-with | 1554.79 |
| fully-parameterized-quantile-function-for | 3165.3 |
| asynchronous-methods-for-deep-reinforcement | 173.0 |
| learning-values-across-many-orders-of | 782.5 |
| asynchronous-methods-for-deep-reinforcement | 263.9 |
| dueling-network-architectures-for-deep | 2296.8 |
| evolving-simple-programs-for-playing-atari | 199 |
| prioritized-experience-replay | 129.1 |
| generalized-data-distribution-iteration | 1065 |
| prioritized-experience-replay | 1838.9 |
| online-and-offline-reinforcement-learning-by | 1197.38 |
| evolution-strategies-as-a-scalable | 112.0 |
| Model 46 | 183.6 |
| deep-exploration-via-bootstrapped-dqn | 1272.5 |
| mastering-atari-go-chess-and-shogi-by | 28634.39 |