OpenCodePapers

atari-games-on-atari-2600-ice-hockey

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
Generalized Data Distribution Iteration481.9GDI-H32022-06-07
Recurrent Experience Replay in Distributed Reinforcement Learning✓ Link79.3R2D22019-05-01
Mastering Atari, Go, Chess and Shogi by Planning with a Learned Model✓ Link67.04MuZero2019-11-19
Agent57: Outperforming the Atari Human Benchmark✓ Link63.64Agent572020-03-30
GDI: Rethinking What Makes Reinforcement Learning Different From Supervised Learning44.94GDI-I32021-06-11
Generalized Data Distribution Iteration44.94GDI-I32022-06-07
Online and Offline Reinforcement Learning by Planning with a Learned Model✓ Link41.66MuZero (Res2 Adam)2021-04-13
The Arcade Learning Environment: An Evaluation Platform for General Agents✓ Link39.4UCT2012-07-19
Distributed Prioritized Experience Replay✓ Link33Ape-X2018-03-02
Mastering Atari with Discrete World Models✓ Link26DreamerV22020-10-05
Fully Parameterized Quantile Function for Distributional Reinforcement Learning✓ Link17.3FQF2019-11-05
DNA: Proximal Policy Optimization with a Dual Network Architecture✓ Link7.2DNA2022-06-20
Evolving simple programs for playing Atari games✓ Link4CGP2018-06-14
IMPALA: Scalable Distributed Deep-RL with Importance Weighted Actor-Learner Architectures✓ Link3.48IMPALA (deep)2018-02-05
Noisy Networks for Exploration✓ Link3NoisyNet-Dueling2017-06-30
Prioritized Experience Replay✓ Link1.3Prior noop2015-11-18
Dueling Network Architectures for Deep Reinforcement Learning✓ Link0.5Duel noop2015-11-20
Deep Reinforcement Learning with Double Q-learning✓ Link0.5Prior+Duel hs2015-09-22
Implicit Quantile Networks for Distributional Reinforcement Learning✓ Link0.2IQN2018-06-14
[]()-3.2SARSA
Human level control through deep reinforcement learning✓ Link-1.6Nature DQN2015-02-25
Massively Parallel Methods for Deep Reinforcement Learning✓ Link-1.7Gorila2015-07-15
Deep Reinforcement Learning with Double Q-learning✓ Link-1.6DQN hs2015-09-22
Deep Reinforcement Learning with Double Q-learning✓ Link-1.9DQN noop2015-09-22
Dueling Network Architectures for Deep Reinforcement Learning✓ Link-1.3Duel hs2015-11-20
Dueling Network Architectures for Deep Reinforcement Learning✓ Link-2.7DDQN (tuned) noop2015-11-20
Deep Reinforcement Learning with Double Q-learning✓ Link-2.5DDQN (tuned) hs2015-09-22
Prioritized Experience Replay✓ Link-0.2Prior hs2015-11-18
Learning values across many orders of magnitude-4.1DDQN+Pop-Art noop2016-02-24
Dueling Network Architectures for Deep Reinforcement Learning✓ Link-0.4Prior+Duel noop2015-11-20
Asynchronous Methods for Deep Reinforcement Learning✓ Link-1.7A3C LSTM hs2016-02-04
Asynchronous Methods for Deep Reinforcement Learning✓ Link-2.8A3C FF hs2016-02-04
Asynchronous Methods for Deep Reinforcement Learning✓ Link-4.7A3C FF (1 day) hs2016-02-04
Evolution Strategies as a Scalable Alternative to Reinforcement Learning✓ Link-4.1ES FF (1 hour) noop2017-03-10
A Distributional Perspective on Reinforcement Learning✓ Link-3.5C51 noop2017-07-21
Deep Exploration via Bootstrapped DQN✓ Link-1.3Bootstrapped DQN2016-02-15
Increasing the Action Gap: New Operators for Reinforcement Learning✓ Link-0.25Persistent AL2015-12-15
Increasing the Action Gap: New Operators for Reinforcement Learning✓ Link-1.24Advantage Learning2015-12-15
Distributional Reinforcement Learning with Quantile Regression✓ Link-1.7QR-DQN-12017-10-27
Self-Imitation Learning✓ Link-2.4A2C + SIL2018-06-14
Policy Optimization With Penalized Point Probability Distance: An Alternative To Proximal Policy Optimization✓ Link-4.12POP3D2018-07-02
The Arcade Learning Environment: An Evaluation Platform for General Agents✓ Link-9.5Best Learner2012-07-19
Train a Real-world Local Path Planner in One Hour via Partially Decoupled Reinforcement Learning and Vectorized Diversity✓ Link-3.6ASL DDQN2023-05-07
Check out how to contribute new results.