OpenCodePapers

atari-games-on-atari-2600-up-and-down

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
GDI: Rethinking What Makes Reinforcement Learning Different From Supervised Learning986440GDI-I32021-06-11
Generalized Data Distribution Iteration986440GDI-I32022-06-07
Generalized Data Distribution Iteration966590GDI-H32022-06-07
Mastering Atari, Go, Chess and Shogi by Planning with a Learned Model✓ Link715545.61MuZero2019-11-19
Mastering Atari with Discrete World Models✓ Link653662DreamerV22020-10-05
Online and Offline Reinforcement Learning by Planning with a Learned Model✓ Link634898.18MuZero (Res2 Adam)2021-04-13
Agent57: Outperforming the Atari Human Benchmark✓ Link623805.73Agent572020-03-30
Recurrent Experience Replay in Distributed Reinforcement Learning✓ Link589226.9R2D22019-05-01
Distributed Prioritized Experience Replay✓ Link401884.3Ape-X2018-03-02
Recurrent Independent Mechanisms✓ Link390000RIMs-PPO2019-09-24
IMPALA: Scalable Distributed Deep-RL with Importance Weighted Actor-Learner Architectures✓ Link332546.75IMPALA (deep)2018-02-05
DNA: Proximal Policy Optimization with a Dual Network Architecture✓ Link291934DNA2022-06-20
Policy Optimization With Penalized Point Probability Distance: An Alternative To Proximal Policy Optimization✓ Link242701.51POP3D2018-07-02
Asynchronous Methods for Deep Reinforcement Learning✓ Link105728.7A3C LSTM hs2016-02-04
Implicit Quantile Networks for Distributional Reinforcement Learning✓ Link88148IQN2018-06-14
Asynchronous Methods for Deep Reinforcement Learning✓ Link74705.7A3C FF hs2016-02-04
The Arcade Learning Environment: An Evaluation Platform for General Agents✓ Link74473.6UCT2012-07-19
Distributional Reinforcement Learning with Quantile Regression✓ Link71260QR-DQN-12017-10-27
Evolution Strategies as a Scalable Alternative to Reinforcement Learning✓ Link67974.0ES FF (1 hour) noop2017-03-10
Noisy Networks for Exploration✓ Link61326NoisyNet-Dueling2017-06-30
Asynchronous Methods for Deep Reinforcement Learning✓ Link54525.4A3C FF (1 day) hs2016-02-04
Self-Imitation Learning✓ Link53314.6A2C + SIL2018-06-14
Dueling Network Architectures for Deep Reinforcement Learning✓ Link44939.6Duel noop2015-11-20
Dueling Network Architectures for Deep Reinforcement Learning✓ Link33879.1Prior+Duel noop2015-11-20
Deep Exploration via Bootstrapped DQN✓ Link26231Bootstrapped DQN2016-02-15
Train a Real-world Local Path Planner in One Hour via Partially Decoupled Reinforcement Learning and Vectorized Diversity✓ Link25127.4ASL DDQN2023-05-07
Dueling Network Architectures for Deep Reinforcement Learning✓ Link24759.2Duel hs2015-11-20
Dueling Network Architectures for Deep Reinforcement Learning✓ Link22972.2DDQN (tuned) noop2015-11-20
Deep Reinforcement Learning with Double Q-learning✓ Link22681.3Prior+Duel hs2015-09-22
Learning values across many orders of magnitude22474.4DDQN+Pop-Art noop2016-02-24
Deep Reinforcement Learning with Double Q-learning✓ Link19086.9DDQN (tuned) hs2015-09-22
Prioritized Experience Replay✓ Link16154.1Prior noop2015-11-18
A Distributional Perspective on Reinforcement Learning✓ Link15612.0C51 noop2017-07-21
Evolving simple programs for playing Atari games✓ Link14524CGP2018-06-14
Increasing the Action Gap: New Operators for Reinforcement Learning✓ Link13909.74Advantage Learning2015-12-15
Prioritized Experience Replay✓ Link12157.4Prior hs2015-11-18
Deep Reinforcement Learning with Double Q-learning✓ Link9989.9DQN noop2015-09-22
Massively Parallel Methods for Deep Reinforcement Learning✓ Link8747.7Gorila2015-07-15
Human level control through deep reinforcement learning✓ Link8456.0Nature DQN2015-02-25
Deep Reinforcement Learning with Double Q-learning✓ Link8038.5DQN hs2015-09-22
The Arcade Learning Environment: An Evaluation Platform for General Agents✓ Link3532.7Best Learner2012-07-19
CURL: Contrastive Unsupervised Representations for Reinforcement Learning✓ Link2735.2CURL2020-04-08
[]()2449.0SARSA
Soft Actor-Critic for Discrete Action Settings✓ Link250.7SAC2019-10-16
Check out how to contribute new results.