Atari Games On Atari 2600 River Raid

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
asynchronous-methods-for-deep-reinforcement	6591.9
generalized-data-distribution-iteration	28075
dueling-network-architectures-for-deep	21162.6
massively-parallel-methods-for-deep	5310.3
human-level-control-through-deep	8316.0
mastering-atari-go-chess-and-shogi-by	323417.18
a-distributional-perspective-on-reinforcement	17322.0
learning-values-across-many-orders-of	12530.8
deep-reinforcement-learning-with-double-q	4748.5
the-arcade-learning-environment-an-evaluation	4449
dueling-network-architectures-for-deep	14884.5
dueling-network-architectures-for-deep	20607.6
dna-proximal-policy-optimization-with-a-dual	16789
asynchronous-methods-for-deep-reinforcement	12201.8
recurrent-experience-replay-in-distributed	45632.1
asynchronous-methods-for-deep-reinforcement	10001.2
deep-reinforcement-learning-with-double-q	10838.4
fully-parameterized-quantile-function-for	23560.7
generalized-data-distribution-iteration	28349
evolution-strategies-as-a-scalable	5009.0
agent57-outperforming-the-atari-human	63318.67
モデル 22	2650.0
implicit-quantile-networks-for-distributional	17765
policy-optimization-with-penalized-point	8052.23
deep-exploration-via-bootstrapped-dqn	12845
mastering-atari-with-discrete-world-models-1	16351
online-and-offline-reinforcement-learning-by	171673.78
model-free-episodic-control-with-state	3868
train-a-real-world-local-path-planner-in-one	24445
deep-reinforcement-learning-with-double-q	7377.6
self-imitation-learning	14306.1
prioritized-experience-replay	11807.2
impala-scalable-distributed-deep-rl-with	29608.05
increasing-the-action-gap-new-operators-for	10585.12
distributed-prioritized-experience-replay	63864.4
deep-reinforcement-learning-with-double-q	16496.8
dueling-network-architectures-for-deep	16569.4
prioritized-experience-replay	14522.3
evolving-simple-programs-for-playing-atari	2914
the-arcade-learning-environment-an-evaluation	1904.3
distributional-reinforcement-learning-with-1	17571