Atari Games On Atari 2600 Kangaroo
평가 지표
Score
평가 결과
이 벤치마크에서 각 모델의 성능 결과
비교 표
| 모델 이름 | Score |
|---|---|
| noisy-networks-for-exploration | 15227 |
| distributional-reinforcement-learning-with-1 | 15356 |
| gdi-rethinking-what-makes-reinforcement | 14500 |
| distributed-prioritized-experience-replay | 1416 |
| mastering-atari-go-chess-and-shogi-by | 16763.60 |
| deep-reinforcement-learning-with-double-q | 4496.0 |
| human-level-control-through-deep | 6740.0 |
| online-and-offline-reinforcement-learning-by | 13838 |
| increasing-the-action-gap-new-operators-for | 10809.16 |
| implicit-quantile-networks-for-distributional | 15487 |
| prioritized-experience-replay | 16200.0 |
| dueling-network-architectures-for-deep | 1792.0 |
| agent57-outperforming-the-atari-human | 24034.16 |
| train-a-real-world-local-path-planner-in-one | 13027 |
| 모델 15 | 8.8 |
| asynchronous-methods-for-deep-reinforcement | 94.0 |
| evolution-strategies-as-a-scalable | 11200.0 |
| deep-reinforcement-learning-with-double-q | 11204.0 |
| dueling-network-architectures-for-deep | 12992.0 |
| asynchronous-methods-for-deep-reinforcement | 106.0 |
| recurrent-rational-networks | 2941 |
| the-arcade-learning-environment-an-evaluation | 1622.1 |
| policy-optimization-with-penalized-point | 3891.67 |
| evolving-simple-programs-for-playing-atari | 1400 |
| the-arcade-learning-environment-an-evaluation | 1990 |
| a-distributional-perspective-on-reinforcement | 12853.0 |
| mastering-atari-with-discrete-world-models-1 | 14064 |
| generalized-data-distribution-iteration | 14636 |
| playing-atari-with-six-neurons | 1200 |
| deep-exploration-via-bootstrapped-dqn | 14862.5 |
| dna-proximal-policy-optimization-with-a-dual | 14373 |
| curl-contrastive-unsupervised-representations | 345.3 |
| dueling-network-architectures-for-deep | 10334.0 |
| recurrent-rational-networks | 5266 |
| impala-scalable-distributed-deep-rl-with | 1632.00 |
| massively-parallel-methods-for-deep | 1431.0 |
| self-imitation-learning | 2888.3 |
| asynchronous-methods-for-deep-reinforcement | 125.0 |
| learning-values-across-many-orders-of | 13150.0 |
| deep-reinforcement-learning-with-double-q | 861.0 |
| prioritized-experience-replay | 12185.0 |
| recurrent-experience-replay-in-distributed | 14130.7 |
| deep-reinforcement-learning-with-double-q | 7259.0 |
| generalized-data-distribution-iteration | 14500 |
| soft-actor-critic-for-discrete-action | 29.3 |
| increasing-the-action-gap-new-operators-for | 11478.46 |
| dueling-network-architectures-for-deep | 14854.0 |