Atari Games On Atari 2600 Frostbite
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 |
|---|---|
| learning-values-across-many-orders-of | 3469.6 |
| asynchronous-methods-for-deep-reinforcement | 197.6 |
| increasing-the-action-gap-new-operators-for | 3248.96 |
| dna-proximal-policy-optimization-with-a-dual | 320 |
| dueling-network-architectures-for-deep | 2332.4 |
| deep-reinforcement-learning-with-double-q | 797.4 |
| dueling-network-architectures-for-deep | 7413.0 |
| incentivizing-exploration-in-reinforcement | 507.0 |
| recurrent-experience-replay-in-distributed | 315456.4 |
| evolution-strategies-as-a-scalable | 370.0 |
| the-arcade-learning-environment-an-evaluation | 216.9 |
| deep-reinforcement-learning-with-double-q | 4038.4 |
| exploration-a-study-of-count-based | 5214.0 |
| mastering-atari-go-chess-and-shogi-by | 631378.53 |
| prioritized-experience-replay | 3510.0 |
| deep-exploration-via-bootstrapped-dqn | 2181.4 |
| curl-contrastive-unsupervised-representations | 924 |
| prioritized-experience-replay | 4380.1 |
| asynchronous-methods-for-deep-reinforcement | 190.5 |
| value-prediction-network | 3811 |
| モデル 21 | 180.9 |
| a-distributional-perspective-on-reinforcement | 3965.0 |
| the-arcade-learning-environment-an-evaluation | 270.5 |
| mastering-atari-with-discrete-world-models-1 | 11384 |
| online-and-offline-reinforcement-learning-by | 374769.76 |
| human-level-control-through-deep | 328.3 |
| dueling-network-architectures-for-deep | 4672.8 |
| increasing-the-action-gap-new-operators-for | 2305.82 |
| implicit-quantile-networks-for-distributional | 4324 |
| deep-reinforcement-learning-with-double-q | 496.1 |
| fully-parameterized-quantile-function-for | 214060 |
| massively-parallel-methods-for-deep | 426.6 |
| self-imitation-learning | 6289.8 |
| playing-atari-with-six-neurons | 300 |
| deep-reinforcement-learning-with-double-q | 1448.1 |
| model-free-episodic-control-with-state | 2394 |
| dueling-network-architectures-for-deep | 1683.3 |
| asynchronous-methods-for-deep-reinforcement | 180.1 |
| count-based-exploration-in-feature-space-for | 2770.1 |
| distributed-prioritized-experience-replay | 9328.6 |
| distributional-reinforcement-learning-with-1 | 4384 |
| generalized-data-distribution-iteration | 11330 |
| noisy-networks-for-exploration | 2923 |
| gdi-rethinking-what-makes-reinforcement | 10485 |
| evolving-simple-programs-for-playing-atari | 782 |
| train-a-real-world-local-path-planner-in-one | 8616.4 |
| policy-optimization-with-penalized-point | 316.87 |
| impala-scalable-distributed-deep-rl-with | 317.75 |
| soft-actor-critic-for-discrete-action | 59.4 |
| generalized-data-distribution-iteration | 11330 |
| count-based-exploration-in-feature-space-for | 1394.3 |
| generalized-data-distribution-iteration | 10485 |
| agent57-outperforming-the-atari-human | 541280.88 |