SOTAVerified

Atari Games

The Atari 2600 Games task (and dataset) involves training an agent to achieve high game scores.

( Image credit: Playing Atari with Deep Reinforcement Learning )

Papers

Recently AddedMost HypedMost ActiveNeeds VerificationMost Verified

Showing 151–200 of 625 papers

TitleStatusHype
Mask Atari for Deep Reinforcement Learning as POMDP Benchmarks—0
Learning Relational Rules from RewardsCode0
NavDreams: Towards Camera-Only RL Navigation Among HumansCode1
Lazy-MDPs: Towards Interpretable Reinforcement Learning by Learning When to Act—0
Improving the Diversity of Bootstrapped DQN by Replacing Priors With Noise—0
On the Generalization of Representations in Reinforcement LearningCode0
A Unified Perspective on Value Backup and Exploration in Monte-Carlo Tree Search—0
ExPoSe: Combining State-Based Exploration with Gradient-Based Online SearchCode0
Distributional Reinforcement Learning with Regularized Wasserstein LossCode0
Deep Reinforcement Learning with Spiking Q-learning—0
Exploration by Random Network Distillation—0
Attention Option-Critic—0
Execute Order 66: Targeted Data Poisoning for Reinforcement Learning—0
A Theoretical Understanding of Gradient Bias in Meta-Reinforcement LearningCode0
Deep Reinforcement Learning Policies Learn Shared Adversarial Features Across MDPs—0
Conjugated Discrete Distributions for Distributional Reinforcement LearningCode0
Human-Level Control through Directly-Trained Deep Spiking Q-NetworksCode1
Continual Learning In Environments With Polynomial Mixing TimesCode0
A Benchmark for Low-Switching-Cost Reinforcement Learning—0
DR3: Value-Based Deep Reinforcement Learning Requires Explicit Regularization—0
A Review for Deep Reinforcement Learning in Atari:Benchmarks, Challenges, and Solutions—0
Hybrid Self-Attention NEAT: A novel evolutionary approach to improve the NEAT algorithmCode1
Virtual Replay CacheCode0
Target Entropy Annealing for Discrete Soft Actor-Critic—0
NovelD: A Simple yet Effective Exploration CriterionCode1
Improving Experience Replay with Successor Representation—0
A Review for Deep Reinforcement Learning in Atari: Benchmarks, Challenges, and Solutions—0
GDI: Rethinking What Makes Reinforcement Learning Different from Supervised Learning—0
Fast and Data-Efficient Training of Rainbow: an Experimental Study on AtariCode1
Improving Experience Replay through Modeling of Similar Transitions' SetsCode0
Mastering Atari Games with Limited DataCode2
Effects of Different Optimization Formulations in Evolutionary Reinforcement Learning on Diverse Behavior Generation—0
Explaining Deep Reinforcement Learning Agents In The Atari Domain through a Surrogate Model—0
The Benefits of Being Categorical Distributional: Uncertainty-aware Regularized Exploration in Reinforcement Learning—0
How to Sense the World: Leveraging Hierarchy in Multimodal Perception for Robust Reinforcement Learning AgentsCode0
Large Batch Experience ReplayCode1
An Unsupervised Video Game Playstyle Metric via State DiscretizationCode0
Is Policy Learning Overrated?: Width-Based Planning and Active Learning for AtariCode0
Self-Supervised Structured Representations for Deep Reinforcement Learning—0
Deep Learning of Intrinsically Motivated Options in the Arcade Learning Environment—0
P4O: Efficient Deep Reinforcement Learning with Predictive Processing Proximal Policy Optimization—0
Training with Worst-Case Distributional Shift causes Overestimation and Inaccuracies in State-Action Value Functions—0
Distributional Perturbation for Efficient Exploration in Distributional Reinforcement Learning—0
Maximizing Ensemble Diversity in Deep Reinforcement Learning—0
Towards Understanding Distributional Reinforcement Learning: Regularization, Optimization, Acceleration and Sinkhorn Algorithm—0
CrowdPlay: Crowdsourcing human demonstration data for offline learning in Atari games—0
Faster Reinforcement Learning with Value Target Lower Bounding—0
EqR: Equivariant Representations for Data-Efficient Reinforcement Learning—0
Should I Run Offline Reinforcement Learning or Behavioral Cloning?—0
On Bonus-Based Exploration Methods in the Arcade Learning Environment—0
Show:102550
← PrevPage 4 of 13Next →
All datasetsAtari 2600 BreakoutAtari 2600 FreewayAtari 2600 Q*BertAtari 2600 SeaquestAtari 2600 VentureAtari 2600 Space InvadersAtari 2600 FrostbiteAtari 2600 GravitarAtari 2600 PongAtari 2600 Private EyeAtari 2600 Montezuma's RevengeAtari 2600 Alien

Benchmark Results

#ModelMetricClaimedVerifiedStatus
1GDI-I3(200M frames)Score864—Unverified
2GDI-H3(200M frames)Score864—Unverified
3GDI-H3Score864—Unverified
4GDI-I3Score864—Unverified
5Bootstrapped DQNScore855—Unverified
6FQFScore854.2—Unverified
7R2D2Score837.7—Unverified
8Ape-XScore800.9—Unverified
9Agent57Score790.4—Unverified
10IMPALA (deep)Score787.34—Unverified
#ModelMetricClaimedVerifiedStatus
1IQNScore34—Unverified
2QR-DQN-1Score34—Unverified
3TRPO-hashScore34—Unverified
4NoisyNet-DuelingScore34—Unverified
5GDI-H3Score34—Unverified
6GDI-H3(200M frames)Score34—Unverified
7GDI-I3Score34—Unverified
8Go-ExploreScore34—Unverified
9Bootstrapped DQNScore33.9—Unverified
10C51 noopScore33.9—Unverified
#ModelMetricClaimedVerifiedStatus
1Agent57Score580,328.14—Unverified
2QR-DQN-1Score572,510—Unverified
3R2D2Score408,850—Unverified
4IMPALA (deep)Score351,200.12—Unverified
5Ape-XScore302,391.3—Unverified
6A2C + SILScore104,975.6—Unverified
7MuZero (Res2 Adam)Score94,906.25—Unverified
8DreamerV2Score94,688—Unverified
9MuZeroScore72,276—Unverified
10DNAScore52,398—Unverified
#ModelMetricClaimedVerifiedStatus
1GDI-H3Score1,000,000—Unverified
2GDI-H3(200M frames)Score1,000,000—Unverified
3Agent57Score999,997.63—Unverified
4R2D2Score999,996.7—Unverified
5MuZeroScore999,976.52—Unverified
6MuZero (Res2 Adam)Score999,659.18—Unverified
7GDI-I3Score943,910—Unverified
8Ape-XScore392,952.3—Unverified
9C51 noopScore266,434—Unverified
10Duel noopScore50,254.2—Unverified