Atari Games On Atari 2600 Enduro
Metrics
Score
Results
Performance results of various models on this benchmark
Comparison Table
| Model Name | Score |
|---|---|
| deep-reinforcement-learning-with-double-q | 626.7 |
| increasing-the-action-gap-new-operators-for | 1252.7 |
| implicit-quantile-networks-for-distributional | 2359 |
| playing-atari-with-deep-reinforcement | 661 |
| prioritized-experience-replay | 2093.0 |
| dna-proximal-policy-optimization-with-a-dual | 2059 |
| train-a-real-world-local-path-planner-in-one | 2103.1 |
| human-level-control-through-deep | 301.8 |
| increasing-the-action-gap-new-operators-for | 1343.1 |
| dueling-network-architectures-for-deep | 2306.4 |
| asynchronous-methods-for-deep-reinforcement | -82.5 |
| asynchronous-methods-for-deep-reinforcement | -82.5 |
| evolving-simple-programs-for-playing-atari | 56.8 |
| the-arcade-learning-environment-an-evaluation | 286.3 |
| gdi-rethinking-what-makes-reinforcement | 14330 |
| dueling-network-architectures-for-deep | 2077.4 |
| recurrent-rational-networks | 1043 |
| deep-reinforcement-learning-with-double-q | 729.0 |
| value-prediction-network | 382 |
| dueling-network-architectures-for-deep | 2258.2 |
| generalized-data-distribution-iteration | 14300 |
| impala-scalable-distributed-deep-rl-with | 0.00 |
| mastering-atari-go-chess-and-shogi-by | 2382.44 |
| massively-parallel-methods-for-deep | 71.0 |
| policy-optimization-with-penalized-point | 459.85 |
| mastering-atari-with-discrete-world-models-1 | 1656 |
| distributional-reinforcement-learning-with-1 | 2355 |
| online-and-offline-reinforcement-learning-by | 2365.81 |
| asynchronous-methods-for-deep-reinforcement | -82.2 |
| self-imitation-learning | 1205.1 |
| prioritized-experience-replay | 1831.0 |
| the-arcade-learning-environment-an-evaluation | 129.1 |
| dueling-network-architectures-for-deep | 1211.8 |
| agent57-outperforming-the-atari-human | 2367.71 |
| recurrent-rational-networks | 957 |
| Model 36 | 159.4 |
| recurrent-experience-replay-in-distributed | 2372.7 |
| deep-exploration-via-bootstrapped-dqn | 1591 |
| noisy-networks-for-exploration | 2013 |
| the-reactor-a-fast-and-sample-efficient-actor | 2224.2 |
| evolution-strategies-as-a-scalable | 95.0 |
| deep-reinforcement-learning-with-double-q | 1216.6 |
| a-distributional-perspective-on-reinforcement | 3454.0 |
| soft-actor-critic-for-discrete-action | 0.8 |
| learning-values-across-many-orders-of | 2002.1 |
| deep-reinforcement-learning-with-double-q | 2223.9 |
| generalized-data-distribution-iteration | 14330 |
| distributed-prioritized-experience-replay | 2177.4 |