OpenCodePapers

atari-games-on-atari-2600-breakout

Video GamesAtari Games
Dataset Link
Results over time
Click legend items to toggle metrics. Hover points for model names.
Leaderboard
Click a sortable column header to sort.
PaperCodeScoreModelNameReleaseDate
Generalized Data Distribution Iteration864.00GDI-H3(200M frames)2022-06-07
Generalized Data Distribution Iteration864.00GDI-I3(200M frames)2022-06-07
Generalized Data Distribution Iteration864.00GDI-I32022-06-07
Generalized Data Distribution Iteration864GDI-H32022-06-07
Deep Exploration via Bootstrapped DQN✓ Link855Bootstrapped DQN2016-02-15
Fully Parameterized Quantile Function for Distributional Reinforcement Learning✓ Link854.2FQF2019-11-05
Recurrent Experience Replay in Distributed Reinforcement Learning✓ Link837.7R2D22019-05-01
Distributed Prioritized Experience Replay✓ Link800.9Ape-X2018-03-02
Agent57: Outperforming the Atari Human Benchmark✓ Link790.4Agent572020-03-30
IMPALA: Scalable Distributed Deep-RL with Importance Weighted Actor-Learner Architectures✓ Link787.34IMPALA (deep)2018-02-05
Asynchronous Methods for Deep Reinforcement Learning✓ Link766.8A3C LSTM hs2016-02-04
Online and Offline Reinforcement Learning by Planning with a Learned Model✓ Link758.04MuZero (Res2 Adam)2021-04-13
A Distributional Perspective on Reinforcement Learning✓ Link748.0C51 noop2017-07-21
Distributional Reinforcement Learning with Quantile Regression✓ Link742QR-DQN-12017-10-27
Implicit Quantile Networks for Distributional Reinforcement Learning✓ Link734IQN2018-06-14
Asynchronous Methods for Deep Reinforcement Learning✓ Link681.9A3C FF hs2016-02-04
DNA: Proximal Policy Optimization with a Dual Network Architecture✓ Link626DNA2022-06-20
Train a Real-world Local Path Planner in One Hour via Partially Decoupled Reinforcement Learning and Vectorized Diversity✓ Link621.7ASL DDQN2023-05-07
Asynchronous Methods for Deep Reinforcement Learning✓ Link551.6A3C FF (1 day) hs2016-02-04
The Reactor: A fast and sample-efficient Actor-Critic agent for Reinforcement Learning514.8Reactor 500M2017-04-15
Policy Optimization With Penalized Point Probability Distance: An Alternative To Proximal Policy Optimization✓ Link458.41POP3D2018-07-02
Self-Imitation Learning✓ Link452A2C + SIL2018-06-14
Increasing the Action Gap: New Operators for Reinforcement Learning✓ Link431.89Persistent AL2015-12-15
Increasing the Action Gap: New Operators for Reinforcement Learning✓ Link425.32Advantage Learning2015-12-15
Dueling Network Architectures for Deep Reinforcement Learning✓ Link418.5DDQN (tuned) noop2015-11-20
Dueling Network Architectures for Deep Reinforcement Learning✓ Link411.6Duel hs2015-11-20
Human level control through deep reinforcement learning✓ Link401.2Nature DQN2015-02-25
Deep Reinforcement Learning with Double Q-learning✓ Link385.5DQN noop2015-09-22
Prioritized Experience Replay✓ Link373.9Prior noop2015-11-18
Mean Actor Critic✓ Link372.7MAC2017-09-01
Deep Reinforcement Learning with Double Q-learning✓ Link368.9DDQN (tuned) hs2015-09-22
Dueling Network Architectures for Deep Reinforcement Learning✓ Link366.0Prior+Duel noop2015-11-20
The Arcade Learning Environment: An Evaluation Platform for General Agents✓ Link364.4UCT2012-07-19
Deep Reinforcement Learning with Double Q-learning✓ Link354.6Prior+Duel hs2015-09-22
Deep Reinforcement Learning with Double Q-learning✓ Link354.5DQN hs2015-09-22
Distributed Deep Reinforcement Learning: Learn how to play Atari games in 21 minutes✓ Link350DDRL A3C2018-01-09
Dueling Network Architectures for Deep Reinforcement Learning✓ Link345.3Duel noop2015-11-20
Learning values across many orders of magnitude344.1DDQN+Pop-Art noop2016-02-24
Prioritized Experience Replay✓ Link343.0Prior hs2015-11-18
Adaptive Rational Activations to Boost Deep Reinforcement Learning✓ Link336Recurrent Rational DQN Average2021-02-18
Adaptive Rational Activations to Boost Deep Reinforcement Learning✓ Link316Rational DQN Average2021-02-18
Massively Parallel Methods for Deep Reinforcement Learning✓ Link313.0Gorila2015-07-15
Mastering Atari with Discrete World Models✓ Link312DreamerV22020-10-05
Decision Transformer: Reinforcement Learning via Sequence Modeling✓ Link267.5DT2021-06-02
Noisy Networks for Exploration✓ Link263NoisyNet-Dueling2017-06-30
Playing Atari with Deep Reinforcement Learning✓ Link225DQN Best2013-12-19
Optimizing the Neural Architecture of Reinforcement Learning Agents✓ Link180.6SPOS2020-11-30
Optimizing the Neural Architecture of Reinforcement Learning Agents✓ Link161.1ENAS Search space 12020-11-30
Optimizing the Neural Architecture of Reinforcement Learning Agents✓ Link144.4SPOS Search space 12020-11-30
Optimizing the Neural Architecture of Reinforcement Learning Agents✓ Link91.4ENAS2020-11-30
Deep Attention Recurrent Q-Network✓ Link20DARQN hard2015-12-05
CURL: Contrastive Unsupervised Representations for Reinforcement Learning✓ Link18.2CURL2020-04-08
Evolving simple programs for playing Atari games✓ Link13.2CGP2018-06-14
Smaller World Models for Reinforcement Learning11.6Discrete Latent Space World Model (VQ-VAE)2020-10-12
Evolution Strategies as a Scalable Alternative to Reinforcement Learning✓ Link9.5ES FF (1 hour) noop2017-03-10
[]()6.1SARSA
The Arcade Learning Environment: An Evaluation Platform for General Agents✓ Link5.2Best Learner2012-07-19
Soft Actor-Critic for Discrete Action Settings✓ Link0.7SAC2019-10-16
Check out how to contribute new results.