Atari Games On Atari 2600 Ms Pacman
평가 지표
Score
평가 결과
이 벤치마크에서 각 모델의 성능 결과
비교 표
| 모델 이름 | Score |
|---|---|
| asynchronous-methods-for-deep-reinforcement | 653.7 |
| evolving-simple-programs-for-playing-atari | 2568 |
| 모델 3 | 1227.0 |
| human-level-control-through-deep | 2311.0 |
| gdi-rethinking-what-makes-reinforcement | 11536 |
| the-arcade-learning-environment-an-evaluation | 1691.8 |
| curl-contrastive-unsupervised-representations | 1492.8 |
| noisy-networks-for-exploration | 5546 |
| model-free-episodic-control-with-state | 8530.4004 |
| fully-parameterized-quantile-function-for | 7631.9 |
| policy-optimization-with-penalized-point | 1683.87 |
| online-and-offline-reinforcement-learning-by | 70659.76 |
| distributed-prioritized-experience-replay | 11255.2 |
| deep-reinforcement-learning-with-double-q | 3085.6 |
| self-imitation-learning | 4025.1 |
| the-arcade-learning-environment-an-evaluation | 22336 |
| dueling-network-architectures-for-deep | 3327.3 |
| deep-reinforcement-learning-with-double-q | 1241.3 |
| distributional-reinforcement-learning-with-1 | 5821 |
| dueling-network-architectures-for-deep | 2711.4 |
| mastering-atari-with-discrete-world-models-1 | 5652 |
| dueling-network-architectures-for-deep | 6283.5 |
| implicit-quantile-networks-for-distributional | 6349 |
| dna-proximal-policy-optimization-with-a-dual | 5894 |
| asynchronous-methods-for-deep-reinforcement | 850.7 |
| deep-reinforcement-learning-with-double-q | 1007.8 |
| recurrent-experience-replay-in-distributed | 42281.7 |
| mastering-atari-go-chess-and-shogi-by | 243401.10 |
| a-distributional-perspective-on-reinforcement | 3415.0 |
| train-a-real-world-local-path-planner-in-one | 4416 |
| impala-scalable-distributed-deep-rl-with | 7342.32 |
| increasing-the-action-gap-new-operators-for | 3917.55 |
| value-prediction-network | 2689 |
| prioritized-experience-replay | 6518.7 |
| generalized-data-distribution-iteration | 11573 |
| dueling-network-architectures-for-deep | 2250.6 |
| generalized-data-distribution-iteration | 11536 |
| agent57-outperforming-the-atari-human | 63994.44 |
| prioritized-experience-replay | 1865.9 |
| soft-actor-critic-for-discrete-action | 690.9 |
| deep-reinforcement-learning-with-double-q | 1092.3 |
| asynchronous-methods-for-deep-reinforcement | 594.4 |
| deep-exploration-via-bootstrapped-dqn | 2983.3 |
| increasing-the-action-gap-new-operators-for | 4065.8 |
| massively-parallel-methods-for-deep | 1263.0 |
| learning-values-across-many-orders-of | 4963.8 |
| rainbow-combining-improvements-in-deep | 2570.2 |