OpenCodePapers

atari-games-on-atari-2600-gopher

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 Iteration488830GDI-I32022-06-07
Generalized Data Distribution Iteration473560GDI-H32022-06-07
Mastering Atari, Go, Chess and Shogi by Planning with a Learned Model✓ Link130345.58MuZero2019-11-19
Recurrent Experience Replay in Distributed Reinforcement Learning✓ Link124776.3R2D22019-05-01
Online and Offline Reinforcement Learning by Planning with a Learned Model✓ Link122882.5MuZero (Res2 Adam)2021-04-13
Distributed Prioritized Experience Replay✓ Link120500.9Ape-X2018-03-02
Implicit Quantile Networks for Distributional Reinforcement Learning✓ Link118365IQN2018-06-14
Agent57: Outperforming the Atari Human Benchmark✓ Link117777.08Agent572020-03-30
Distributional Reinforcement Learning with Quantile Regression✓ Link113585QR-DQN-12017-10-27
Deep Reinforcement Learning with Double Q-learning✓ Link105148.4Prior+Duel hs2015-09-22
Dueling Network Architectures for Deep Reinforcement Learning✓ Link104368.2Prior+Duel noop2015-11-20
Train a Real-world Local Path Planner in One Hour via Partially Decoupled Reinforcement Learning and Vectorized Diversity✓ Link103514.4ASL DDQN2023-05-07
Mastering Atari with Discrete World Models✓ Link92282DreamerV22020-10-05
DNA: Proximal Policy Optimization with a Dual Network Architecture✓ Link80104DNA2022-06-20
IMPALA: Scalable Distributed Deep-RL with Importance Weighted Actor-Learner Architectures✓ Link66782.30IMPALA (deep)2018-02-05
Learning values across many orders of magnitude56218.2DDQN+Pop-Art noop2016-02-24
Noisy Networks for Exploration✓ Link38909NoisyNet-Dueling2017-06-30
Prioritized Experience Replay✓ Link34858.8Prior hs2015-11-18
A Distributional Perspective on Reinforcement Learning✓ Link33641.0C51 noop2017-07-21
Prioritized Experience Replay✓ Link32487.2Prior noop2015-11-18
Self-Imitation Learning✓ Link23304.2A2C + SIL2018-06-14
The Arcade Learning Environment: An Evaluation Platform for General Agents✓ Link20560UCT2012-07-19
Dueling Network Architectures for Deep Reinforcement Learning✓ Link20051.4Duel hs2015-11-20
Deep Exploration via Bootstrapped DQN✓ Link17438.4Bootstrapped DQN2016-02-15
Asynchronous Methods for Deep Reinforcement Learning✓ Link17106.8A3C LSTM hs2016-02-04
Dueling Network Architectures for Deep Reinforcement Learning✓ Link15718.4Duel noop2015-11-20
Deep Reinforcement Learning with Double Q-learning✓ Link15253.0DDQN (tuned) hs2015-09-22
Dueling Network Architectures for Deep Reinforcement Learning✓ Link14840.8DDQN (tuned) noop2015-11-20
Increasing the Action Gap: New Operators for Reinforcement Learning✓ Link11912.68Advantage Learning2015-12-15
Increasing the Action Gap: New Operators for Reinforcement Learning✓ Link10611.81Persistent AL2015-12-15
Asynchronous Methods for Deep Reinforcement Learning✓ Link10022.8A3C FF hs2016-02-04
Deep Reinforcement Learning with Double Q-learning✓ Link8777.4DQN noop2015-09-22
Human level control through deep reinforcement learning✓ Link8520.0Nature DQN2015-02-25
Asynchronous Methods for Deep Reinforcement Learning✓ Link8442.8A3C FF (1 day) hs2016-02-04
Deep Reinforcement Learning with Double Q-learning✓ Link8190.4DQN hs2015-09-22
Policy Optimization With Penalized Point Probability Distance: An Alternative To Proximal Policy Optimization✓ Link6207POP3D2018-07-02
Deep Attention Recurrent Q-Network✓ Link5356DARQN soft2015-12-05
Massively Parallel Methods for Deep Reinforcement Learning✓ Link4373.0Gorila2015-07-15
[]()2368.0SARSA
Evolving simple programs for playing Atari games✓ Link1696CGP2018-06-14
The Arcade Learning Environment: An Evaluation Platform for General Agents✓ Link1288.3Best Learner2012-07-19
CURL: Contrastive Unsupervised Representations for Reinforcement Learning✓ Link801.4CURL2020-04-08
Evolution Strategies as a Scalable Alternative to Reinforcement Learning✓ Link582.0ES FF (1 hour) noop2017-03-10
Check out how to contribute new results.