Atari Games On Atari 2600 Gopher
Metrics
Score
Results
Performance results of various models on this benchmark
Comparison Table
| Model Name | Score |
|---|---|
| distributional-reinforcement-learning-with-1 | 113585 |
| prioritized-experience-replay | 34858.8 |
| asynchronous-methods-for-deep-reinforcement | 10022.8 |
| the-arcade-learning-environment-an-evaluation | 20560 |
| human-level-control-through-deep | 8520.0 |
| massively-parallel-methods-for-deep | 4373.0 |
| deep-reinforcement-learning-with-double-q | 8777.4 |
| evolution-strategies-as-a-scalable | 582.0 |
| Model 9 | 2368.0 |
| impala-scalable-distributed-deep-rl-with | 66782.30 |
| dueling-network-architectures-for-deep | 104368.2 |
| dueling-network-architectures-for-deep | 15718.4 |
| policy-optimization-with-penalized-point | 6207 |
| dueling-network-architectures-for-deep | 14840.8 |
| generalized-data-distribution-iteration | 473560 |
| learning-values-across-many-orders-of | 56218.2 |
| evolving-simple-programs-for-playing-atari | 1696 |
| deep-reinforcement-learning-with-double-q | 15253.0 |
| increasing-the-action-gap-new-operators-for | 10611.81 |
| online-and-offline-reinforcement-learning-by | 122882.5 |
| curl-contrastive-unsupervised-representations | 801.4 |
| asynchronous-methods-for-deep-reinforcement | 17106.8 |
| train-a-real-world-local-path-planner-in-one | 103514.4 |
| dueling-network-architectures-for-deep | 20051.4 |
| self-imitation-learning | 23304.2 |
| mastering-atari-go-chess-and-shogi-by | 130345.58 |
| dna-proximal-policy-optimization-with-a-dual | 80104 |
| deep-exploration-via-bootstrapped-dqn | 17438.4 |
| mastering-atari-with-discrete-world-models-1 | 92282 |
| asynchronous-methods-for-deep-reinforcement | 8442.8 |
| implicit-quantile-networks-for-distributional | 118365 |
| prioritized-experience-replay | 32487.2 |
| deep-attention-recurrent-q-network | 5356 |
| deep-reinforcement-learning-with-double-q | 105148.4 |
| deep-reinforcement-learning-with-double-q | 8190.4 |
| increasing-the-action-gap-new-operators-for | 11912.68 |
| the-arcade-learning-environment-an-evaluation | 1288.3 |
| recurrent-experience-replay-in-distributed | 124776.3 |
| a-distributional-perspective-on-reinforcement | 33641.0 |
| agent57-outperforming-the-atari-human | 117777.08 |
| generalized-data-distribution-iteration | 488830 |
| distributed-prioritized-experience-replay | 120500.9 |
| noisy-networks-for-exploration | 38909 |