OpenCodePapers

atari-games-on-atari-2600-seaquest

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.
PaperCodeScoreReturnModelNameReleaseDate
Generalized Data Distribution Iteration1000000GDI-H3(200M frames)2022-06-07
Generalized Data Distribution Iteration1000000GDI-H32022-06-07
Agent57: Outperforming the Atari Human Benchmark✓ Link999997.63Agent572020-03-30
Recurrent Experience Replay in Distributed Reinforcement Learning✓ Link999996.7R2D22019-05-01
Mastering Atari, Go, Chess and Shogi by Planning with a Learned Model✓ Link999976.52MuZero2019-11-19
Online and Offline Reinforcement Learning by Planning with a Learned Model✓ Link999659.18MuZero (Res2 Adam)2021-04-13
Generalized Data Distribution Iteration943910GDI-I32022-06-07
GDI: Rethinking What Makes Reinforcement Learning Different From Supervised Learning943910GDI-I32021-06-11
Distributed Prioritized Experience Replay✓ Link392952.3Ape-X2018-03-02
A Distributional Perspective on Reinforcement Learning✓ Link266434.0C51 noop2017-07-21
Dueling Network Architectures for Deep Reinforcement Learning✓ Link50254.2Duel noop2015-11-20
Dueling Network Architectures for Deep Reinforcement Learning✓ Link37361.6Duel hs2015-11-20
Implicit Quantile Networks for Distributional Reinforcement Learning✓ Link30140IQN2018-06-14
Train a Real-world Local Path Planner in One Hour via Partially Decoupled Reinforcement Learning and Vectorized Diversity✓ Link29278.6ASL DDQN2023-05-07
Prioritized Experience Replay✓ Link26357.8Prior noop2015-11-18
Prioritized Experience Replay✓ Link25463.7Prior hs2015-11-18
Noisy Networks for Exploration✓ Link16754NoisyNet-Dueling2017-06-30
Dueling Network Architectures for Deep Reinforcement Learning✓ Link16452.7DDQN (tuned) noop2015-11-20
Deep Reinforcement Learning with Double Q-learning✓ Link14498.0DDQN (tuned) hs2015-09-22
Increasing the Action Gap: New Operators for Reinforcement Learning✓ Link13230.74Persistent AL2015-12-15
Learning values across many orders of magnitude10932.3DDQN+Pop-Art noop2016-02-24
Massively Parallel Methods for Deep Reinforcement Learning✓ Link10145.9Gorila2015-07-15
Deep Exploration via Bootstrapped DQN✓ Link9083.1Bootstrapped DQN2016-02-15
Increasing the Action Gap: New Operators for Reinforcement Learning✓ Link8670.5Advantage Learning2015-12-15
Distributional Reinforcement Learning with Quantile Regression✓ Link8268QR-DQN-12017-10-27
Mastering Atari with Discrete World Models✓ Link7480DreamerV22020-10-05
Adaptive Rational Activations to Boost Deep Reinforcement Learning✓ Link7460Recurrent Rational DQN Average2021-02-18
Deep Attention Recurrent Q-Network✓ Link7263DARQN soft2015-12-05
Adaptive Rational Activations to Boost Deep Reinforcement Learning✓ Link6603Rational DQN Average2021-02-18
Deep Reinforcement Learning with Double Q-learning✓ Link5860.6DQN noop2015-09-22
Value Prediction Network✓ Link5628VPN2017-07-11
Human level control through deep reinforcement learning✓ Link5286.0Nature DQN2015-02-25
The Arcade Learning Environment: An Evaluation Platform for General Agents✓ Link5132.4UCT2012-07-19
Deep Reinforcement Learning with Double Q-learning✓ Link4216.7DQN hs2015-09-22
DNA: Proximal Policy Optimization with a Dual Network Architecture✓ Link4146DNA2022-06-20
Self-Imitation Learning✓ Link2456.5A2C + SIL2018-06-14
Asynchronous Methods for Deep Reinforcement Learning✓ Link2355.4A3C FF hs2016-02-04
Asynchronous Methods for Deep Reinforcement Learning✓ Link2300.2A3C FF (1 day) hs2016-02-04
Distributed Deep Reinforcement Learning: Learn how to play Atari games in 21 minutes✓ Link1832DDRL A3C2018-01-09
Policy Optimization With Penalized Point Probability Distance: An Alternative To Proximal Policy Optimization✓ Link1807.47POP3D2018-07-02
IMPALA: Scalable Distributed Deep-RL with Importance Weighted Actor-Learner Architectures✓ Link1753.20IMPALA (deep)2018-02-05
Playing Atari with Deep Reinforcement Learning✓ Link1740DQN Best2013-12-19
Mean Actor Critic✓ Link1703.4MAC2017-09-01
Deep Reinforcement Learning with Double Q-learning✓ Link1431.2Prior+Duel hs2015-09-22
Evolution Strategies as a Scalable Alternative to Reinforcement Learning✓ Link1390.0ES FF (1 hour) noop2017-03-10
Asynchronous Methods for Deep Reinforcement Learning✓ Link1326.1A3C LSTM hs2016-02-04
Dueling Network Architectures for Deep Reinforcement Learning✓ Link931.6Prior+Duel noop2015-11-20
Evolving simple programs for playing Atari games✓ Link724CGP2018-06-14
[]()675.5SARSA
The Arcade Learning Environment: An Evaluation Platform for General Agents✓ Link664.8Best Learner2012-07-19
Smaller World Models for Reinforcement Learning635Discrete Latent Space World Model (VQ-VAE)2020-10-12
Improving Computational Efficiency in Visual Reinforcement Learning via Stored Embeddings✓ Link561.2Rainbow+SEER2021-03-04
CURL: Contrastive Unsupervised Representations for Reinforcement Learning✓ Link408CURL2020-04-08
Playing Atari with Six Neurons✓ Link320IDVQ + DRSC + XNES2018-06-04
Soft Actor-Critic for Discrete Action Settings✓ Link211.6SAC2019-10-16
Decision Transformer: Reinforcement Learning via Sequence Modeling✓ Link2.4DT2021-06-02
IQ-Learn: Inverse soft-Q Learning for Imitation✓ Link2349IQ-Learn2021-06-23
Check out how to contribute new results.