OpenCodePapers

atari-games-on-atari-2600-ms-pacman

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.
PaperCodeScoreBest ScoreModelNameReleaseDate
Mastering Atari, Go, Chess and Shogi by Planning with a Learned Model✓ Link243401.10MuZero2019-11-19
Online and Offline Reinforcement Learning by Planning with a Learned Model✓ Link70659.76MuZero (Res2 Adam)2021-04-13
Agent57: Outperforming the Atari Human Benchmark✓ Link63994.44Agent572020-03-30
Recurrent Experience Replay in Distributed Reinforcement Learning✓ Link42281.7R2D22019-05-01
The Arcade Learning Environment: An Evaluation Platform for General Agents✓ Link22336UCT2012-07-19
Generalized Data Distribution Iteration11573GDI-H32022-06-07
GDI: Rethinking What Makes Reinforcement Learning Different From Supervised Learning11536GDI-I32021-06-11
Generalized Data Distribution Iteration11536GDI-I32022-06-07
Distributed Prioritized Experience Replay✓ Link11255.2Ape-X2018-03-02
Model-Free Episodic Control with State Aggregation8530.400411301MFEC2020-08-21
Fully Parameterized Quantile Function for Distributional Reinforcement Learning✓ Link7631.9FQF2019-11-05
IMPALA: Scalable Distributed Deep-RL with Importance Weighted Actor-Learner Architectures✓ Link7342.32IMPALA (deep)2018-02-05
Prioritized Experience Replay✓ Link6518.7Prior noop2015-11-18
Implicit Quantile Networks for Distributional Reinforcement Learning✓ Link6349IQN2018-06-14
Dueling Network Architectures for Deep Reinforcement Learning✓ Link6283.5Duel noop2015-11-20
DNA: Proximal Policy Optimization with a Dual Network Architecture✓ Link5894DNA2022-06-20
Distributional Reinforcement Learning with Quantile Regression✓ Link5821QR-DQN-12017-10-27
Mastering Atari with Discrete World Models✓ Link5652DreamerV22020-10-05
Noisy Networks for Exploration✓ Link5546NoisyNet-Dueling2017-06-30
Learning values across many orders of magnitude4963.8DDQN+Pop-Art noop2016-02-24
Train a Real-world Local Path Planner in One Hour via Partially Decoupled Reinforcement Learning and Vectorized Diversity✓ Link4416ASL DDQN2023-05-07
Increasing the Action Gap: New Operators for Reinforcement Learning✓ Link4065.8Advantage Learning2015-12-15
Self-Imitation Learning✓ Link4025.1A2C + SIL2018-06-14
Increasing the Action Gap: New Operators for Reinforcement Learning✓ Link3917.55Persistent AL2015-12-15
A Distributional Perspective on Reinforcement Learning✓ Link3415.0C51 noop2017-07-21
Dueling Network Architectures for Deep Reinforcement Learning✓ Link3327.3Prior+Duel noop2015-11-20
Deep Reinforcement Learning with Double Q-learning✓ Link3085.6DQN noop2015-09-22
Deep Exploration via Bootstrapped DQN✓ Link2983.3Bootstrapped DQN2016-02-15
Dueling Network Architectures for Deep Reinforcement Learning✓ Link2711.4DDQN (tuned) noop2015-11-20
Value Prediction Network✓ Link2689VPN2017-07-11
Rainbow: Combining Improvements in Deep Reinforcement Learning✓ Link2570.2Rainbow2017-10-06
Evolving simple programs for playing Atari games✓ Link2568CGP2018-06-14
Human level control through deep reinforcement learning✓ Link2311.0Nature DQN2015-02-25
Dueling Network Architectures for Deep Reinforcement Learning✓ Link2250.6Duel hs2015-11-20
Prioritized Experience Replay✓ Link1865.9Prior hs2015-11-18
The Arcade Learning Environment: An Evaluation Platform for General Agents✓ Link1691.8Best Learner2012-07-19
Policy Optimization With Penalized Point Probability Distance: An Alternative To Proximal Policy Optimization✓ Link1683.87POP3D2018-07-02
CURL: Contrastive Unsupervised Representations for Reinforcement Learning✓ Link1492.8CURL2020-04-08
Massively Parallel Methods for Deep Reinforcement Learning✓ Link1263.0Gorila2015-07-15
Deep Reinforcement Learning with Double Q-learning✓ Link1241.3DDQN (tuned) hs2015-09-22
[]()1227.0SARSA
Deep Reinforcement Learning with Double Q-learning✓ Link1092.3DQN hs2015-09-22
Deep Reinforcement Learning with Double Q-learning✓ Link1007.8Prior+Duel hs2015-09-22
Asynchronous Methods for Deep Reinforcement Learning✓ Link850.7A3C LSTM hs2016-02-04
Soft Actor-Critic for Discrete Action Settings✓ Link690.9SAC2019-10-16
Asynchronous Methods for Deep Reinforcement Learning✓ Link653.7A3C FF hs2016-02-04
Asynchronous Methods for Deep Reinforcement Learning✓ Link594.4A3C FF (1 day) hs2016-02-04
Check out how to contribute new results.