OpenCodePapers

atari-games-on-atari-2600-river-raid

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✓ Link323417.18MuZero2019-11-19
Online and Offline Reinforcement Learning by Planning with a Learned Model✓ Link171673.78MuZero (Res2 Adam)2021-04-13
Distributed Prioritized Experience Replay✓ Link63864.4Ape-X2018-03-02
Agent57: Outperforming the Atari Human Benchmark✓ Link63318.67Agent572020-03-30
Recurrent Experience Replay in Distributed Reinforcement Learning✓ Link45632.1R2D22019-05-01
IMPALA: Scalable Distributed Deep-RL with Importance Weighted Actor-Learner Architectures✓ Link29608.05IMPALA (deep)2018-02-05
Generalized Data Distribution Iteration28349GDI-H32022-06-07
Generalized Data Distribution Iteration28075GDI-I32022-06-07
Train a Real-world Local Path Planner in One Hour via Partially Decoupled Reinforcement Learning and Vectorized Diversity✓ Link24445ASL DDQN2023-05-07
Fully Parameterized Quantile Function for Distributional Reinforcement Learning✓ Link23560.7FQF2019-11-05
Dueling Network Architectures for Deep Reinforcement Learning✓ Link21162.6Duel noop2015-11-20
Dueling Network Architectures for Deep Reinforcement Learning✓ Link20607.6Prior+Duel noop2015-11-20
Implicit Quantile Networks for Distributional Reinforcement Learning✓ Link17765IQN2018-06-14
Distributional Reinforcement Learning with Quantile Regression✓ Link17571QR-DQN-12017-10-27
A Distributional Perspective on Reinforcement Learning✓ Link17322.0C51 noop2017-07-21
DNA: Proximal Policy Optimization with a Dual Network Architecture✓ Link16789DNA2022-06-20
Dueling Network Architectures for Deep Reinforcement Learning✓ Link16569.4Duel hs2015-11-20
Deep Reinforcement Learning with Double Q-learning✓ Link16496.8Prior+Duel hs2015-09-22
Mastering Atari with Discrete World Models✓ Link16351DreamerV22020-10-05
Dueling Network Architectures for Deep Reinforcement Learning✓ Link14884.5DDQN (tuned) noop2015-11-20
Prioritized Experience Replay✓ Link14522.3Prior noop2015-11-18
Self-Imitation Learning✓ Link14306.1A2C + SIL2018-06-14
Deep Exploration via Bootstrapped DQN✓ Link12845Bootstrapped DQN2016-02-15
Learning values across many orders of magnitude12530.8DDQN+Pop-Art noop2016-02-24
Asynchronous Methods for Deep Reinforcement Learning✓ Link12201.8A3C FF hs2016-02-04
Prioritized Experience Replay✓ Link11807.2Prior hs2015-11-18
Deep Reinforcement Learning with Double Q-learning✓ Link10838.4DDQN (tuned) hs2015-09-22
Increasing the Action Gap: New Operators for Reinforcement Learning✓ Link10585.12Advantage Learning2015-12-15
Asynchronous Methods for Deep Reinforcement Learning✓ Link10001.2A3C FF (1 day) hs2016-02-04
Human level control through deep reinforcement learning✓ Link8316.0Nature DQN2015-02-25
Policy Optimization With Penalized Point Probability Distance: An Alternative To Proximal Policy Optimization✓ Link8052.23POP3D2018-07-02
Deep Reinforcement Learning with Double Q-learning✓ Link7377.6DQN noop2015-09-22
Asynchronous Methods for Deep Reinforcement Learning✓ Link6591.9A3C LSTM hs2016-02-04
Massively Parallel Methods for Deep Reinforcement Learning✓ Link5310.3Gorila2015-07-15
Evolution Strategies as a Scalable Alternative to Reinforcement Learning✓ Link5009.0ES FF (1 hour) noop2017-03-10
Deep Reinforcement Learning with Double Q-learning✓ Link4748.5DQN hs2015-09-22
The Arcade Learning Environment: An Evaluation Platform for General Agents✓ Link4449UCT2012-07-19
Model-Free Episodic Control with State Aggregation38685080MFEC2020-08-21
Evolving simple programs for playing Atari games✓ Link2914CGP2018-06-14
[]()2650.0SARSA
The Arcade Learning Environment: An Evaluation Platform for General Agents✓ Link1904.3Best Learner2012-07-19
Check out how to contribute new results.