Atari Games On Atari 2600 Battle Zone
評価指標
Score
評価結果
このベンチマークにおける各モデルのパフォーマンス結果
比較表
| モデル名 | Score |
|---|---|
| soft-actor-critic-for-discrete-action | 4386.7 |
| policy-optimization-with-penalized-point | 15466.67 |
| deep-exploration-via-bootstrapped-dqn | 38666.7 |
| mastering-atari-go-chess-and-shogi-by | 848623.00 |
| dueling-network-architectures-for-deep | 31320.0 |
| impala-scalable-distributed-deep-rl-with | 20885.00 |
| a-distributional-perspective-on-reinforcement | 28742.0 |
| asynchronous-methods-for-deep-reinforcement | 12950.0 |
| prioritized-experience-replay | 25520.0 |
| recurrent-experience-replay-in-distributed | 751880.0 |
| dueling-network-architectures-for-deep | 37150.0 |
| learning-values-across-many-orders-of | 8220.0 |
| distributed-prioritized-experience-replay | 98895 |
| noisy-networks-for-exploration | 52262 |
| agent57-outperforming-the-atari-human | 934134.88 |
| dna-proximal-policy-optimization-with-a-dual | 71003 |
| mastering-atari-with-discrete-world-models-1 | 40325 |
| evolving-simple-programs-for-playing-atari | 34200 |
| fully-parameterized-quantile-function-for | 87928.6 |
| implicit-quantile-networks-for-distributional | 42244 |
| train-a-real-world-local-path-planner-in-one | 38986 |
| prioritized-experience-replay | 31530.0 |
| evolution-strategies-as-a-scalable | 16600.0 |
| deep-reinforcement-learning-with-double-q | 30650.0 |
| asynchronous-methods-for-deep-reinforcement | 11340.0 |
| human-level-control-through-deep | 26300.0 |
| the-reactor-a-fast-and-sample-efficient-actor | 64070.0 |
| massively-parallel-methods-for-deep | 19938.0 |
| generalized-data-distribution-iteration | 478830 |
| increasing-the-action-gap-new-operators-for | 28789.29 |
| deep-reinforcement-learning-with-double-q | 29900.0 |
| the-arcade-learning-environment-an-evaluation | 70333.3 |
| distributional-reinforcement-learning-with-1 | 39268 |
| deep-reinforcement-learning-with-double-q | 23750.0 |
| dueling-network-architectures-for-deep | 35520.0 |
| generalized-data-distribution-iteration | 824360 |
| recurrent-rational-networks | 23403 |
| recurrent-rational-networks | 25749 |
| self-imitation-learning | 25075 |
| curl-contrastive-unsupervised-representations | 11208 |
| dueling-network-architectures-for-deep | 31700.0 |
| online-and-offline-reinforcement-learning-by | 178716.9 |
| asynchronous-methods-for-deep-reinforcement | 20760.0 |
| deep-reinforcement-learning-with-double-q | 24740.0 |
| モデル 45 | 16.2 |
| increasing-the-action-gap-new-operators-for | 34583.07 |
| the-arcade-learning-environment-an-evaluation | 15819.7 |