OpenCodePapers

atari-games-on-atari-2600-asterix

Video GamesAtari Games
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 Iteration999999GDI-H32022-06-07
Recurrent Experience Replay in Distributed Reinforcement Learning✓ Link999153.3R2D22019-05-01
Mastering Atari, Go, Chess and Shogi by Planning with a Learned Model✓ Link998425.00MuZero2019-11-19
Agent57: Outperforming the Atari Human Benchmark✓ Link991384.42Agent572020-03-30
Online and Offline Reinforcement Learning by Planning with a Learned Model✓ Link862406.65MuZero (Res2 Adam)2021-04-13
Generalized Data Distribution Iteration759910GDI-I32022-06-07
Fully Parameterized Quantile Function for Distributional Reinforcement Learning✓ Link578388.5FQF2019-11-05
Train a Real-world Local Path Planner in One Hour via Partially Decoupled Reinforcement Learning and Vectorized Diversity✓ Link567640ASL DDQN2023-05-07
A Distributional Perspective on Reinforcement Learning✓ Link406211C51 noop2017-07-21
Dueling Network Architectures for Deep Reinforcement Learning✓ Link375080.0Prior+Duel noop2015-11-20
Deep Reinforcement Learning with Double Q-learning✓ Link364200.0Prior+Duel hs2015-09-22
Dueling Network Architectures for Deep Reinforcement Learning✓ Link364200.0Prior+Duel hs2015-11-20
Implicit Quantile Networks for Distributional Reinforcement Learning✓ Link342016IQN2018-06-14
DNA: Proximal Policy Optimization with a Dual Network Architecture✓ Link323965DNA2022-06-20
Distributed Prioritized Experience Replay✓ Link313305Ape-X2018-03-02
IMPALA: Scalable Distributed Deep-RL with Importance Weighted Actor-Learner Architectures✓ Link300732.00IMPALA (deep)2018-02-05
The Arcade Learning Environment: An Evaluation Platform for General Agents✓ Link290700UCT2012-07-19
Distributional Reinforcement Learning with Quantile Regression✓ Link261025QR-DQN-12017-10-27
The Reactor: A fast and sample-efficient Actor-Critic agent for Reinforcement Learning205914.0Reactor 500M2017-04-15
Mastering Atari with Discrete World Models✓ Link72311DreamerV22020-10-05
Prioritized Experience Replay✓ Link31527Prior noop2015-11-18
Noisy Networks for Exploration✓ Link28350NoisyNet-Dueling2017-06-30
Dueling Network Architectures for Deep Reinforcement Learning✓ Link28188.0Duel noop2015-11-20
Prioritized Experience Replay✓ Link22484.5Prior hs2015-11-18
Asynchronous Methods for Deep Reinforcement Learning✓ Link22140.5A3C FF hs2016-02-04
[]()21040RIMs-PPO
Deep Exploration via Bootstrapped DQN✓ Link19713.2Bootstrapped DQN2016-02-15
Increasing the Action Gap: New Operators for Reinforcement Learning✓ Link19564.9Persistent AL2015-12-15
Learning values across many orders of magnitude18919.5DDQN+Pop-Art noop2016-02-24
Adaptive Rational Activations to Boost Deep Reinforcement Learning✓ Link18109Rational DQN Average2021-02-18
Self-Imitation Learning✓ Link17984.2A2C + SIL2018-06-14
Dueling Network Architectures for Deep Reinforcement Learning✓ Link17356.5DDQN (tuned) noop2015-11-20
Asynchronous Methods for Deep Reinforcement Learning✓ Link17244.5A3C LSTM hs2016-02-04
Deep Reinforcement Learning with Double Q-learning✓ Link16837.0DDQN (tuned) hs2015-09-22
Dueling Network Architectures for Deep Reinforcement Learning✓ Link15840.0Duel hs2015-11-20
Increasing the Action Gap: New Operators for Reinforcement Learning✓ Link12852.08Advantage Learning2015-12-15
Adaptive Rational Activations to Boost Deep Reinforcement Learning✓ Link12621Recurrent Rational DQN Average2021-02-18
Asynchronous Methods for Deep Reinforcement Learning✓ Link6723A3C FF (1 day) hs2016-02-04
Human level control through deep reinforcement learning✓ Link6012Nature DQN2015-02-25
Deep Reinforcement Learning with Double Q-learning✓ Link4359.0DQN noop2015-09-22
Policy Optimization With Penalized Point Probability Distance: An Alternative To Proximal Policy Optimization✓ Link4310.67POP3D2018-07-02
Massively Parallel Methods for Deep Reinforcement Learning✓ Link3324.7Gorila2015-07-15
Deep Reinforcement Learning with Double Q-learning✓ Link3170.5DQN hs2015-09-22
Evolving simple programs for playing Atari games✓ Link1880CGP2018-06-14
Evolution Strategies as a Scalable Alternative to Reinforcement Learning✓ Link1440ES FF (1 hour) noop2017-03-10
[]()1332SARSA
The Arcade Learning Environment: An Evaluation Platform for General Agents✓ Link987.3Best Learner2012-07-19
CURL: Contrastive Unsupervised Representations for Reinforcement Learning✓ Link524.3CURL2020-04-08
Soft Actor-Critic for Discrete Action Settings✓ Link272SAC2019-10-16
Check out how to contribute new results.