Atari Games On Atari 2600 Berzerk

Metrics

Score

Results

Performance results of various models on this benchmark

Comparison Table

Model Name	Score
fully-parameterized-quantile-function-for	12422.2
asynchronous-methods-for-deep-reinforcement	1433.4
distributed-prioritized-experience-replay	57196.7
implicit-quantile-networks-for-distributional	1053
learning-values-across-many-orders-of	1199.6
deep-reinforcement-learning-with-double-q	1011.1
asynchronous-methods-for-deep-reinforcement	817.9
asynchronous-methods-for-deep-reinforcement	862.2
evolution-strategies-as-a-scalable	686.0
prioritized-experience-replay	1305.6
deep-reinforcement-learning-with-double-q	585.6
gdi-rethinking-what-makes-reinforcement	7607
deep-reinforcement-learning-with-double-q	2178.6
prioritized-experience-replay	865.9
impala-scalable-distributed-deep-rl-with	1852.70
a-distributional-perspective-on-reinforcement	1645.0
the-reactor-a-fast-and-sample-efficient-actor	2303.1
agent57-outperforming-the-atari-human	61507.83
mastering-atari-go-chess-and-shogi-by	85932.60
deep-reinforcement-learning-with-double-q	493.4
dueling-network-architectures-for-deep	1472.6
dueling-network-architectures-for-deep	910.6
train-a-real-world-local-path-planner-in-one	2597.2
increasing-the-action-gap-new-operators-for	1328.25
online-and-offline-reinforcement-learning-by	2705.82
generalized-data-distribution-iteration	7607
dueling-network-architectures-for-deep	1225.4
distributional-reinforcement-learning-with-1	3117
dna-proximal-policy-optimization-with-a-dual	19789
recurrent-experience-replay-in-distributed	53318.7
first-return-then-explore	197376
mastering-atari-with-discrete-world-models-1	810
the-arcade-learning-environment-an-evaluation	670
generalized-data-distribution-iteration	14649
noisy-networks-for-exploration	1896
dueling-network-architectures-for-deep	3409.0
evolving-simple-programs-for-playing-atari	1138
increasing-the-action-gap-new-operators-for	747.26
the-arcade-learning-environment-an-evaluation	501.3