Atari Games On Atari 2600 Robotank

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	64.3
fully-parameterized-quantile-function-for	75.7
recurrent-experience-replay-in-distributed	100.4
prioritized-experience-replay	62.6
increasing-the-action-gap-new-operators-for	69.31
dna-proximal-policy-optimization-with-a-dual	64.8
the-arcade-learning-environment-an-evaluation	50.4
impala-scalable-distributed-deep-rl-with	12.96
dueling-network-architectures-for-deep	65.1
prioritized-experience-replay	56.2
mastering-atari-with-discrete-world-models-1	78
dueling-network-architectures-for-deep	27.5
dueling-network-architectures-for-deep	62.0
モデル 14	12.4
asynchronous-methods-for-deep-reinforcement	2.6
asynchronous-methods-for-deep-reinforcement	32.8
deep-reinforcement-learning-with-double-q	58.7
deep-reinforcement-learning-with-double-q	24.7
train-a-real-world-local-path-planner-in-one	65.8
deep-exploration-via-bootstrapped-dqn	66.6
deep-reinforcement-learning-with-double-q	59.1
generalized-data-distribution-iteration	113.4
noisy-networks-for-exploration	64
deep-reinforcement-learning-with-double-q	63.9
evolution-strategies-as-a-scalable	11.9
distributional-reinforcement-learning-with-1	59.4
distributed-prioritized-experience-replay	73.8
implicit-quantile-networks-for-distributional	62.5
human-level-control-through-deep	51.6
evolving-simple-programs-for-playing-atari	24.2
generalized-data-distribution-iteration	108.2
massively-parallel-methods-for-deep	61.8
mastering-atari-go-chess-and-shogi-by	131.13
policy-optimization-with-penalized-point	4.6
online-and-offline-reinforcement-learning-by	100.59
asynchronous-methods-for-deep-reinforcement	2.3
agent57-outperforming-the-atari-human	127.32
a-distributional-perspective-on-reinforcement	52.3
gdi-rethinking-what-makes-reinforcement	108.2
self-imitation-learning	10.5
the-arcade-learning-environment-an-evaluation	28.7
dueling-network-architectures-for-deep	65.3