OpenCodePapers

atari-games-on-atari-2600-enduro

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
GDI: Rethinking What Makes Reinforcement Learning Different From Supervised Learning14330GDI-I32021-06-11
Generalized Data Distribution Iteration14330GDI-I32022-06-07
Generalized Data Distribution Iteration14300GDI-H32022-06-07
A Distributional Perspective on Reinforcement Learning✓ Link3454.0C51 noop2017-07-21
Mastering Atari, Go, Chess and Shogi by Planning with a Learned Model✓ Link2382.44MuZero2019-11-19
Recurrent Experience Replay in Distributed Reinforcement Learning✓ Link2372.7R2D22019-05-01
Agent57: Outperforming the Atari Human Benchmark✓ Link2367.71Agent572020-03-30
Online and Offline Reinforcement Learning by Planning with a Learned Model✓ Link2365.81MuZero (Res2 Adam)2021-04-13
Implicit Quantile Networks for Distributional Reinforcement Learning✓ Link2359IQN2018-06-14
Distributional Reinforcement Learning with Quantile Regression✓ Link2355QR-DQN-12017-10-27
Dueling Network Architectures for Deep Reinforcement Learning✓ Link2306.4Prior+Duel noop2015-11-20
Dueling Network Architectures for Deep Reinforcement Learning✓ Link2258.2Duel noop2015-11-20
The Reactor: A fast and sample-efficient Actor-Critic agent for Reinforcement Learning2224.2Reactor 500M2017-04-15
Deep Reinforcement Learning with Double Q-learning✓ Link2223.9Prior+Duel hs2015-09-22
Distributed Prioritized Experience Replay✓ Link2177.4Ape-X2018-03-02
Train a Real-world Local Path Planner in One Hour via Partially Decoupled Reinforcement Learning and Vectorized Diversity✓ Link2103.1ASL DDQN2023-05-07
Prioritized Experience Replay✓ Link2093.0Prior noop2015-11-18
Dueling Network Architectures for Deep Reinforcement Learning✓ Link2077.4Duel hs2015-11-20
DNA: Proximal Policy Optimization with a Dual Network Architecture✓ Link2059DNA2022-06-20
Noisy Networks for Exploration✓ Link2013NoisyNet-Dueling2017-06-30
Learning values across many orders of magnitude2002.1DDQN+Pop-Art noop2016-02-24
Prioritized Experience Replay✓ Link1831.0Prior hs2015-11-18
Mastering Atari with Discrete World Models✓ Link1656DreamerV22020-10-05
Deep Exploration via Bootstrapped DQN✓ Link1591Bootstrapped DQN2016-02-15
Increasing the Action Gap: New Operators for Reinforcement Learning✓ Link1343.1Persistent AL2015-12-15
Increasing the Action Gap: New Operators for Reinforcement Learning✓ Link1252.7Advantage Learning2015-12-15
Deep Reinforcement Learning with Double Q-learning✓ Link1216.6DDQN (tuned) hs2015-09-22
Dueling Network Architectures for Deep Reinforcement Learning✓ Link1211.8DDQN (tuned) noop2015-11-20
Self-Imitation Learning✓ Link1205.1A2C + SIL2018-06-14
Adaptive Rational Activations to Boost Deep Reinforcement Learning✓ Link1043Rational DQN Average2021-02-18
Adaptive Rational Activations to Boost Deep Reinforcement Learning✓ Link957Recurrent Rational DQN Average2021-02-18
Deep Reinforcement Learning with Double Q-learning✓ Link729.0DQN noop2015-09-22
Playing Atari with Deep Reinforcement Learning✓ Link661DQN Best2013-12-19
Deep Reinforcement Learning with Double Q-learning✓ Link626.7DQN hs2015-09-22
Policy Optimization With Penalized Point Probability Distance: An Alternative To Proximal Policy Optimization✓ Link459.85POP3D2018-07-02
Value Prediction Network✓ Link382VPN2017-07-11
Human level control through deep reinforcement learning✓ Link301.8Nature DQN2015-02-25
The Arcade Learning Environment: An Evaluation Platform for General Agents✓ Link286.3UCT2012-07-19
[]()159.4SARSA
The Arcade Learning Environment: An Evaluation Platform for General Agents✓ Link129.1Best Learner2012-07-19
Evolution Strategies as a Scalable Alternative to Reinforcement Learning✓ Link95.0ES FF (1 hour) noop2017-03-10
Massively Parallel Methods for Deep Reinforcement Learning✓ Link71.0Gorila2015-07-15
Evolving simple programs for playing Atari games✓ Link56.8CGP2018-06-14
Soft Actor-Critic for Discrete Action Settings✓ Link0.8SAC2019-10-16
IMPALA: Scalable Distributed Deep-RL with Importance Weighted Actor-Learner Architectures✓ Link0.00IMPALA (deep)2018-02-05
Asynchronous Methods for Deep Reinforcement Learning✓ Link-82.2A3C FF (1 day) hs2016-02-04
Asynchronous Methods for Deep Reinforcement Learning✓ Link-82.5A3C FF hs2016-02-04
Asynchronous Methods for Deep Reinforcement Learning✓ Link-82.5A3C LSTM hs2016-02-04
Check out how to contribute new results.