OpenCodePapers

atari-games-on-atari-2600-kangaroo

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
Agent57: Outperforming the Atari Human Benchmark✓ Link24034.16Agent572020-03-30
Mastering Atari, Go, Chess and Shogi by Planning with a Learned Model✓ Link16763.60MuZero2019-11-19
Prioritized Experience Replay✓ Link16200.0Prior noop2015-11-18
Implicit Quantile Networks for Distributional Reinforcement Learning✓ Link15487IQN2018-06-14
Distributional Reinforcement Learning with Quantile Regression✓ Link15356QR-DQN-12017-10-27
Noisy Networks for Exploration✓ Link15227NoisyNet-Dueling2017-06-30
Deep Exploration via Bootstrapped DQN✓ Link14862.5Bootstrapped DQN2016-02-15
Dueling Network Architectures for Deep Reinforcement Learning✓ Link14854.0Duel noop2015-11-20
Generalized Data Distribution Iteration14636GDI-H32022-06-07
GDI: Rethinking What Makes Reinforcement Learning Different From Supervised Learning14500GDI-I32021-06-11
Generalized Data Distribution Iteration14500GDI-I32022-06-07
DNA: Proximal Policy Optimization with a Dual Network Architecture✓ Link14373DNA2022-06-20
Recurrent Experience Replay in Distributed Reinforcement Learning✓ Link14130.7R2D22019-05-01
Mastering Atari with Discrete World Models✓ Link14064DreamerV22020-10-05
Online and Offline Reinforcement Learning by Planning with a Learned Model✓ Link13838MuZero (Res2 Adam)2021-04-13
Learning values across many orders of magnitude13150.0DDQN+Pop-Art noop2016-02-24
Train a Real-world Local Path Planner in One Hour via Partially Decoupled Reinforcement Learning and Vectorized Diversity✓ Link13027ASL DDQN2023-05-07
Dueling Network Architectures for Deep Reinforcement Learning✓ Link12992.0DDQN (tuned) noop2015-11-20
A Distributional Perspective on Reinforcement Learning✓ Link12853.0C51 noop2017-07-21
Prioritized Experience Replay✓ Link12185.0Prior hs2015-11-18
Increasing the Action Gap: New Operators for Reinforcement Learning✓ Link11478.46Persistent AL2015-12-15
Deep Reinforcement Learning with Double Q-learning✓ Link11204.0DDQN (tuned) hs2015-09-22
Evolution Strategies as a Scalable Alternative to Reinforcement Learning✓ Link11200.0ES FF (1 hour) noop2017-03-10
Increasing the Action Gap: New Operators for Reinforcement Learning✓ Link10809.16Advantage Learning2015-12-15
Dueling Network Architectures for Deep Reinforcement Learning✓ Link10334.0Duel hs2015-11-20
Deep Reinforcement Learning with Double Q-learning✓ Link7259.0DQN noop2015-09-22
Human level control through deep reinforcement learning✓ Link6740.0Nature DQN2015-02-25
Adaptive Rational Activations to Boost Deep Reinforcement Learning✓ Link5266Recurrent Rational DQN Average2021-02-18
Deep Reinforcement Learning with Double Q-learning✓ Link4496.0DQN hs2015-09-22
Policy Optimization With Penalized Point Probability Distance: An Alternative To Proximal Policy Optimization✓ Link3891.67POP3D2018-07-02
Adaptive Rational Activations to Boost Deep Reinforcement Learning✓ Link2941Rational DQN Average2021-02-18
Self-Imitation Learning✓ Link2888.3A2C + SIL2018-06-14
The Arcade Learning Environment: An Evaluation Platform for General Agents✓ Link1990UCT2012-07-19
Dueling Network Architectures for Deep Reinforcement Learning✓ Link1792.0Prior+Duel noop2015-11-20
IMPALA: Scalable Distributed Deep-RL with Importance Weighted Actor-Learner Architectures✓ Link1632.00IMPALA (deep)2018-02-05
The Arcade Learning Environment: An Evaluation Platform for General Agents✓ Link1622.1Best Learner2012-07-19
Massively Parallel Methods for Deep Reinforcement Learning✓ Link1431.0Gorila2015-07-15
Distributed Prioritized Experience Replay✓ Link1416Ape-X2018-03-02
Evolving simple programs for playing Atari games✓ Link1400CGP2018-06-14
Playing Atari with Six Neurons✓ Link1200IDVQ + DRSC + XNES2018-06-04
Deep Reinforcement Learning with Double Q-learning✓ Link861.0Prior+Duel hs2015-09-22
CURL: Contrastive Unsupervised Representations for Reinforcement Learning✓ Link345.3CURL2020-04-08
Asynchronous Methods for Deep Reinforcement Learning✓ Link125.0A3C LSTM hs2016-02-04
Asynchronous Methods for Deep Reinforcement Learning✓ Link106.0A3C FF (1 day) hs2016-02-04
Asynchronous Methods for Deep Reinforcement Learning✓ Link94.0A3C FF hs2016-02-04
Soft Actor-Critic for Discrete Action Settings✓ Link29.3SAC2019-10-16
[]()8.8SARSA
Check out how to contribute new results.