OpenCodePapers

atari-games-on-atari-2600-star-gunner

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
Agent57: Outperforming the Atari Human Benchmark✓ Link839573.53Agent572020-03-30
Recurrent Experience Replay in Distributed Reinforcement Learning✓ Link717344.0R2D22019-05-01
Generalized Data Distribution Iteration677590GDI-H32022-06-07
Mastering Atari, Go, Chess and Shogi by Planning with a Learned Model✓ Link549271.70MuZero2019-11-19
GDI: Rethinking What Makes Reinforcement Learning Different From Supervised Learning465750GDI-I32021-06-11
Generalized Data Distribution Iteration465750GDI-I32022-06-07
Distributed Prioritized Experience Replay✓ Link434342.5Ape-X2018-03-02
IMPALA: Scalable Distributed Deep-RL with Importance Weighted Actor-Learner Architectures✓ Link200625.00IMPALA (deep)2018-02-05
Asynchronous Methods for Deep Reinforcement Learning✓ Link164766.0A3C LSTM hs2016-02-04
Online and Offline Reinforcement Learning by Planning with a Learned Model✓ Link154548.26MuZero (Res2 Adam)2021-04-13
Asynchronous Methods for Deep Reinforcement Learning✓ Link138218.0A3C FF hs2016-02-04
Fully Parameterized Quantile Function for Distributional Reinforcement Learning✓ Link131981.2FQF2019-11-05
Train a Real-world Local Path Planner in One Hour via Partially Decoupled Reinforcement Learning and Vectorized Diversity✓ Link129140ASL DDQN2023-05-07
Deep Reinforcement Learning with Double Q-learning✓ Link127073.0Prior+Duel hs2015-09-22
Dueling Network Architectures for Deep Reinforcement Learning✓ Link125117.0Prior+Duel noop2015-11-20
DNA: Proximal Policy Optimization with a Dual Network Architecture✓ Link104125DNA2022-06-20
Dueling Network Architectures for Deep Reinforcement Learning✓ Link90804.0Duel hs2015-11-20
Dueling Network Architectures for Deep Reinforcement Learning✓ Link89238.0Duel noop2015-11-20
Distributional Reinforcement Learning with Quantile Regression✓ Link77495QR-DQN-12017-10-27
Noisy Networks for Exploration✓ Link75867NoisyNet-Dueling2017-06-30
Implicit Quantile Networks for Distributional Reinforcement Learning✓ Link74677IQN2018-06-14
[]()70000RIMs-PPO
Asynchronous Methods for Deep Reinforcement Learning✓ Link64393.0A3C FF (1 day) hs2016-02-04
Prioritized Experience Replay✓ Link63302.0Prior noop2015-11-18
Prioritized Experience Replay✓ Link61582.0Prior hs2015-11-18
Increasing the Action Gap: New Operators for Reinforcement Learning✓ Link61353.59Advantage Learning2015-12-15
Dueling Network Architectures for Deep Reinforcement Learning✓ Link60142.0DDQN (tuned) noop2015-11-20
Deep Reinforcement Learning with Double Q-learning✓ Link58365.0DDQN (tuned) hs2015-09-22
Human level control through deep reinforcement learning✓ Link57997.0Nature DQN2015-02-25
Deep Exploration via Bootstrapped DQN✓ Link55725Bootstrapped DQN2016-02-15
Deep Reinforcement Learning with Double Q-learning✓ Link54282.0DQN noop2015-09-22
Deep Reinforcement Learning with Double Q-learning✓ Link52970.0DQN hs2015-09-22
A Distributional Perspective on Reinforcement Learning✓ Link49095.0C51 noop2017-07-21
Policy Optimization With Penalized Point Probability Distance: An Alternative To Proximal Policy Optimization✓ Link48984POP3D2018-07-02
Self-Imitation Learning✓ Link31309.2A2C + SIL2018-06-14
Massively Parallel Methods for Deep Reinforcement Learning✓ Link14919.2Gorila2015-07-15
Mastering Atari with Discrete World Models✓ Link7800DreamerV22020-10-05
Evolving simple programs for playing Atari games✓ Link2320CGP2018-06-14
Evolution Strategies as a Scalable Alternative to Reinforcement Learning✓ Link1470.0ES FF (1 hour) noop2017-03-10
The Arcade Learning Environment: An Evaluation Platform for General Agents✓ Link1345Full Tree2012-07-19
The Arcade Learning Environment: An Evaluation Platform for General Agents✓ Link1069.5Best Learner2012-07-19
Learning values across many orders of magnitude589.0DDQN+Pop-Art noop2016-02-24
Human level control through deep reinforcement learning✓ Link9.4SARSA2015-02-25
Check out how to contribute new results.