Atari Games On Atari 2600 Crazy Climber
Metriken
Score
Ergebnisse
Leistungsergebnisse verschiedener Modelle zu diesem Benchmark
Vergleichstabelle
| Modellname | Score |
|---|---|
| a-distributional-perspective-on-reinforcement | 179877.0 |
| asynchronous-methods-for-deep-reinforcement | 101624.0 |
| prioritized-experience-replay | 141161.0 |
| gdi-rethinking-what-makes-reinforcement | 201000 |
| generalized-data-distribution-iteration | 201000 |
| impala-scalable-distributed-deep-rl-with | 136950.00 |
| the-reactor-a-fast-and-sample-efficient-actor | 236422.0 |
| learning-values-across-many-orders-of | 119679.0 |
| recurrent-experience-replay-in-distributed | 366690.7 |
| mastering-atari-with-discrete-world-models-1 | 161839 |
| dueling-network-architectures-for-deep | 143570.0 |
| dueling-network-architectures-for-deep | 117282.0 |
| implicit-quantile-networks-for-distributional | 179082 |
| fully-parameterized-quantile-function-for | 223470.6 |
| asynchronous-methods-for-deep-reinforcement | 112646.0 |
| train-a-real-world-local-path-planner-in-one | 166019 |
| distributed-prioritized-experience-replay | 320426 |
| evolving-simple-programs-for-playing-atari | 12900 |
| deep-exploration-via-bootstrapped-dqn | 137925.9 |
| agent57-outperforming-the-atari-human | 565909.85 |
| generalized-data-distribution-iteration | 241170 |
| dueling-network-architectures-for-deep | 124566.0 |
| value-prediction-network | 54119 |
| dueling-network-architectures-for-deep | 162224.0 |
| improving-computational-efficiency-in-visual | 28066 |
| deep-reinforcement-learning-with-double-q | 110763.0 |
| mastering-atari-go-chess-and-shogi-by | 458315.40 |
| the-arcade-learning-environment-an-evaluation | 98172.2 |
| online-and-offline-reinforcement-learning-by | 158541.58 |
| prioritized-experience-replay | 127512.0 |
| the-arcade-learning-environment-an-evaluation | 23410.6 |
| increasing-the-action-gap-new-operators-for | 130002.71 |
| deep-reinforcement-learning-with-double-q | 113782.0 |
| deep-reinforcement-learning-with-double-q | 98128.0 |
| evolution-strategies-as-a-scalable | 26430.0 |
| Modell 36 | 149.8 |
| discrete-latent-space-world-models-for | 59609.4 |
| soft-actor-critic-for-discrete-action | 3668.7 |
| self-imitation-learning | 130185.8 |
| dna-proximal-policy-optimization-with-a-dual | 131623 |
| massively-parallel-methods-for-deep | 65451.0 |
| curl-contrastive-unsupervised-representations | 27805.6 |
| distributional-reinforcement-learning-with-1 | 161196 |
| asynchronous-methods-for-deep-reinforcement | 138518.0 |
| increasing-the-action-gap-new-operators-for | 123410.71 |
| policy-optimization-with-penalized-point | 120247.33 |
| noisy-networks-for-exploration | 171171 |
| deep-reinforcement-learning-with-double-q | 127853.0 |
| human-level-control-through-deep | 114103.0 |