OpenCodePapers

atari-games-on-atari-2600-name-this-game

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
Mastering Atari, Go, Chess and Shogi by Planning with a Learned Model✓ Link157177.85MuZero2019-11-19
Online and Offline Reinforcement Learning by Planning with a Learned Model✓ Link101197.71MuZero (Res2 Adam)2021-04-13
Recurrent Experience Replay in Distributed Reinforcement Learning✓ Link58182.7R2D22019-05-01
Agent57: Outperforming the Atari Human Benchmark✓ Link54386.77Agent572020-03-30
Generalized Data Distribution Iteration36296GDI-H32022-06-07
GDI: Rethinking What Makes Reinforcement Learning Different From Supervised Learning34434GDI-I32021-06-11
Generalized Data Distribution Iteration34434GDI-I32022-06-07
Distributed Prioritized Experience Replay✓ Link25783.3Ape-X2018-03-02
Implicit Quantile Networks for Distributional Reinforcement Learning✓ Link22682IQN2018-06-14
Distributional Reinforcement Learning with Quantile Regression✓ Link21890QR-DQN-12017-10-27
IMPALA: Scalable Distributed Deep-RL with Importance Weighted Actor-Learner Architectures✓ Link21537.20IMPALA (deep)2018-02-05
DNA: Proximal Policy Optimization with a Dual Network Architecture✓ Link20226DNA2022-06-20
Train a Real-world Local Path Planner in One Hour via Partially Decoupled Reinforcement Learning and Vectorized Diversity✓ Link16535.4ASL DDQN2023-05-07
Learning values across many orders of magnitude15851.2DDQN+Pop-Art noop2016-02-24
Dueling Network Architectures for Deep Reinforcement Learning✓ Link15572.5Prior+Duel noop2015-11-20
The Arcade Learning Environment: An Evaluation Platform for General Agents✓ Link15410UCT2012-07-19
Self-Imitation Learning✓ Link14958.2A2C + SIL2018-06-14
Mastering Atari with Discrete World Models✓ Link14649DreamerV22020-10-05
Deep Reinforcement Learning with Double Q-learning✓ Link13637.9Prior+Duel hs2015-09-22
A Distributional Perspective on Reinforcement Learning✓ Link12542.0C51 noop2017-07-21
Prioritized Experience Replay✓ Link12270.5Prior noop2015-11-18
Noisy Networks for Exploration✓ Link12211NoisyNet-Dueling2017-06-30
Asynchronous Methods for Deep Reinforcement Learning✓ Link12093.7A3C LSTM hs2016-02-04
Dueling Network Architectures for Deep Reinforcement Learning✓ Link11971.1Duel noop2015-11-20
Deep Exploration via Bootstrapped DQN✓ Link11501.1Bootstrapped DQN2016-02-15
Dueling Network Architectures for Deep Reinforcement Learning✓ Link11185.1Duel hs2015-11-20
Increasing the Action Gap: New Operators for Reinforcement Learning✓ Link11025.26Advantage Learning2015-12-15
Dueling Network Architectures for Deep Reinforcement Learning✓ Link10616.0DDQN (tuned) noop2015-11-20
Prioritized Experience Replay✓ Link10497.6Prior hs2015-11-18
Asynchronous Methods for Deep Reinforcement Learning✓ Link10476.1A3C FF hs2016-02-04
Increasing the Action Gap: New Operators for Reinforcement Learning✓ Link10431.33Persistent AL2015-12-15
Massively Parallel Methods for Deep Reinforcement Learning✓ Link9238.5Gorila2015-07-15
Deep Reinforcement Learning with Double Q-learning✓ Link8960.3DDQN (tuned) hs2015-09-22
Deep Reinforcement Learning with Double Q-learning✓ Link8207.8DQN noop2015-09-22
Human level control through deep reinforcement learning✓ Link7257.0Nature DQN2015-02-25
Deep Reinforcement Learning with Double Q-learning✓ Link6738.8DQN hs2015-09-22
Policy Optimization With Penalized Point Probability Distance: An Alternative To Proximal Policy Optimization✓ Link6065.63POP3D2018-07-02
Asynchronous Methods for Deep Reinforcement Learning✓ Link5614.0A3C FF (1 day) hs2016-02-04
Evolution Strategies as a Scalable Alternative to Reinforcement Learning✓ Link4503.0ES FF (1 hour) noop2017-03-10
Evolving simple programs for playing Atari games✓ Link3696CGP2018-06-14
The Arcade Learning Environment: An Evaluation Platform for General Agents✓ Link2500.1Best Learner2012-07-19
[]()2247.0SARSA
Playing Atari with Six Neurons✓ Link920IDVQ + DRSC + XNES2018-06-04
Check out how to contribute new results.