Atari Games On Atari 2600 Beam Rider
Metriken
Score
Ergebnisse
Leistungsergebnisse verschiedener Modelle zu diesem Benchmark
Vergleichstabelle
| Modellname | Score |
|---|---|
| asynchronous-methods-for-deep-reinforcement | 24622.2 |
| prioritized-experience-replay | 23384.2 |
| impala-scalable-distributed-deep-rl-with | 32463.47 |
| deep-reinforcement-learning-with-double-q | 9743.2 |
| learning-values-across-many-orders-of | 8299.4 |
| dueling-network-architectures-for-deep | 12164.0 |
| human-level-control-through-deep | 6846.0 |
| policy-optimization-with-penalized-point | 4549 |
| the-arcade-learning-environment-an-evaluation | 929.4 |
| playing-atari-with-deep-reinforcement | 5184 |
| Modell 11 | 1743.0 |
| mastering-atari-with-discrete-world-models-1 | 18646 |
| massively-parallel-methods-for-deep | 3822.1 |
| recurrent-independent-mechanisms | 5320 |
| dueling-network-architectures-for-deep | 30276.5 |
| asynchronous-methods-for-deep-reinforcement | 13235.9 |
| evolving-simple-programs-for-playing-atari | 1341.6 |
| the-arcade-learning-environment-an-evaluation | 6624.6 |
| iq-learn-inverse-soft-q-learning-for | - |
| online-and-offline-reinforcement-learning-by | 333077.44 |
| agent57-outperforming-the-atari-human | 300509.8 |
| soft-actor-critic-for-discrete-action | 432.1 |
| deep-reinforcement-learning-with-double-q | 37412.2 |
| a-distributional-perspective-on-reinforcement | 14074.0 |
| noisy-networks-for-exploration | 23134 |
| asynchronous-methods-for-deep-reinforcement | 22707.9 |
| recurrent-experience-replay-in-distributed | 188257.4 |
| deep-reinforcement-learning-with-double-q | 17417.2 |
| dueling-network-architectures-for-deep | 13772.8 |
| distributional-reinforcement-learning-with-1 | 34821 |
| mastering-atari-go-chess-and-shogi-by | 454993.53 |
| deep-reinforcement-learning-with-double-q | 8627.5 |
| evolution-strategies-as-a-scalable | 744.0 |
| dueling-network-architectures-for-deep | 14591.3 |
| distributed-deep-reinforcement-learning-learn | 14900 |
| generalized-data-distribution-iteration | 162100 |
| mean-actor-critic | 6072 |
| deep-exploration-via-bootstrapped-dqn | 23429.8 |
| increasing-the-action-gap-new-operators-for | 13145.34 |
| implicit-quantile-networks-for-distributional | 42776 |
| generalized-data-distribution-iteration | 422890 |
| train-a-real-world-local-path-planner-in-one | 26841.6 |
| the-reactor-a-fast-and-sample-efficient-actor | 11033.4 |
| increasing-the-action-gap-new-operators-for | 10054.58 |
| dna-proximal-policy-optimization-with-a-dual | 20393 |
| gdi-rethinking-what-makes-reinforcement | 162100 |
| self-imitation-learning | 2366.2 |
| distributed-prioritized-experience-replay | 63305.2 |
| prioritized-experience-replay | 31181.3 |