Atari Games On Atari 2600 Qbert
Metrics
Score
Results
Performance results of various models on this benchmark
Comparison Table
| Model Name | Score |
|---|---|
| dueling-network-architectures-for-deep | 18760.3 |
| mastering-atari-go-chess-and-shogi-by | 72276.00 |
| dueling-network-architectures-for-deep | 14175.8 |
| deep-reinforcement-learning-with-double-q | 14063.0 |
| a-distributional-perspective-on-reinforcement | 23784 |
| generalized-data-distribution-iteration | 28657 |
| mastering-atari-with-discrete-world-models-1 | 94688 |
| prioritized-experience-replay | 16256.5 |
| implicit-quantile-networks-for-distributional | 25750 |
| dueling-network-architectures-for-deep | 15088.5 |
| value-prediction-network | 14517 |
| count-based-exploration-in-feature-space-for | 3895.3 |
| iq-learn-inverse-soft-q-learning-for | - |
| Model 14 | 960.3 |
| deep-reinforcement-learning-with-double-q | 9271.5 |
| mean-actor-critic | 243.4 |
| incentivizing-exploration-in-reinforcement | 15805 |
| learning-values-across-many-orders-of | 5236.8 |
| playing-atari-with-deep-reinforcement | 4500 |
| generalized-data-distribution-iteration | 27800 |
| deep-exploration-via-bootstrapped-dqn | 15092.7 |
| the-arcade-learning-environment-an-evaluation | 17343.4 |
| asynchronous-methods-for-deep-reinforcement | 21307.5 |
| recurrent-experience-replay-in-distributed | 408850.0 |
| recurrent-rational-networks | 14436 |
| asynchronous-methods-for-deep-reinforcement | 15148.8 |
| the-arcade-learning-environment-an-evaluation | 613.5 |
| distributed-prioritized-experience-replay | 302391.3 |
| decision-transformer-reinforcement-learning | 25.1 |
| agent57-outperforming-the-atari-human | 580328.14 |
| prioritized-experience-replay | 9944 |
| improving-computational-efficiency-in-visual | 4123.5 |
| impala-scalable-distributed-deep-rl-with | 351200.12 |
| recurrent-rational-networks | 14080 |
| distributional-reinforcement-learning-with-1 | 572510 |
| playing-atari-with-six-neurons | 1250 |
| count-based-exploration-in-feature-space-for | 4111.8 |
| policy-optimization-with-penalized-point | 15396.67 |
| deep-reinforcement-learning-with-double-q | 11020.8 |
| massively-parallel-methods-for-deep | 7089.8 |
| increasing-the-action-gap-new-operators-for | 14368.03 |
| dna-proximal-policy-optimization-with-a-dual | 52398 |
| gdi-rethinking-what-makes-reinforcement | 27800 |
| human-level-control-through-deep | 10596 |
| deep-reinforcement-learning-with-double-q | 13117.3 |
| model-free-episodic-control-with-state | 14135 |
| dueling-network-architectures-for-deep | 19220.3 |
| train-a-real-world-local-path-planner-in-one | 24548.8 |
| evolving-simple-programs-for-playing-atari | 770 |
| evolution-strategies-as-a-scalable | 147.5 |
| asynchronous-methods-for-deep-reinforcement | 13752.3 |
| soft-actor-critic-for-discrete-action | 280.5 |
| online-and-offline-reinforcement-learning-by | 94906.25 |
| curl-contrastive-unsupervised-representations | 1225.6 |
| noisy-networks-for-exploration | 27121 |
| self-imitation-learning | 104975.6 |
| generalized-data-distribution-iteration | 28657 |