OpenCodePapers

atari-games-on-atari-2600-bowling

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
Mastering Atari, Go, Chess and Shogi by Planning with a Learned Model✓ Link260.13MuZero2019-11-19
First return, then explore✓ Link260Go-Explore2020-04-27
Agent57: Outperforming the Atari Human Benchmark✓ Link251.18Agent572020-03-30
Recurrent Experience Replay in Distributed Reinforcement Learning✓ Link219.5R2D22019-05-01
Generalized Data Distribution Iteration205.2GDI-H32022-06-07
GDI: Rethinking What Makes Reinforcement Learning Different From Supervised Learning201.9GDI-I32021-06-11
Generalized Data Distribution Iteration201.9GDI-I32022-06-07
DNA: Proximal Policy Optimization with a Dual Network Architecture✓ Link181DNA2022-06-20
RUDDER: Return Decomposition for Delayed Rewards✓ Link179RUDDER2018-06-20
Online and Offline Reinforcement Learning by Planning with a Learned Model✓ Link131.65MuZero (Res2 Adam)2021-04-13
Fully Parameterized Quantile Function for Distributional Reinforcement Learning✓ Link102.3FQF2019-11-05
Learning values across many orders of magnitude102.1DDQN+Pop-Art noop2016-02-24
Implicit Quantile Networks for Distributional Reinforcement Learning✓ Link86.5IQN2018-06-14
Evolving simple programs for playing Atari games✓ Link85.8CGP2018-06-14
A Distributional Perspective on Reinforcement Learning✓ Link81.8C51 noop2017-07-21
The Reactor: A fast and sample-efficient Actor-Critic agent for Reinforcement Learning81.0Reactor 500M2017-04-15
Distributional Reinforcement Learning with Quantile Regression✓ Link77.2QR-DQN-12017-10-27
Increasing the Action Gap: New Operators for Reinforcement Learning✓ Link71.59Persistent AL2015-12-15
Deep Reinforcement Learning with Double Q-learning✓ Link69.6DDQN (tuned) hs2015-09-22
Dueling Network Architectures for Deep Reinforcement Learning✓ Link68.1DDQN (tuned) noop2015-11-20
Dueling Network Architectures for Deep Reinforcement Learning✓ Link65.7Duel hs2015-11-20
Dueling Network Architectures for Deep Reinforcement Learning✓ Link65.5Duel noop2015-11-20
Train a Real-world Local Path Planner in One Hour via Partially Decoupled Reinforcement Learning and Vectorized Diversity✓ Link62.4ASL DDQN2023-05-07
Deep Exploration via Bootstrapped DQN✓ Link60.2Bootstrapped DQN2016-02-15
IMPALA: Scalable Distributed Deep-RL with Importance Weighted Actor-Learner Architectures✓ Link59.92IMPALA (deep)2018-02-05
Increasing the Action Gap: New Operators for Reinforcement Learning✓ Link57.41Advantage Learning2015-12-15
Deep Reinforcement Learning with Double Q-learning✓ Link56.5DQN hs2015-09-22
Massively Parallel Methods for Deep Reinforcement Learning✓ Link54Gorila2015-07-15
Prioritized Experience Replay✓ Link52Prior hs2015-11-18
Deep Reinforcement Learning with Double Q-learning✓ Link50.4DQN noop2015-09-22
Deep Reinforcement Learning with Double Q-learning✓ Link50.4Prior+Duel hs2015-09-22
Mastering Atari with Discrete World Models✓ Link49DreamerV22020-10-05
Prioritized Experience Replay✓ Link47.9Prior noop2015-11-18
Dueling Network Architectures for Deep Reinforcement Learning✓ Link46.7Prior+Duel noop2015-11-20
The Arcade Learning Environment: An Evaluation Platform for General Agents✓ Link43.9Best Learner2012-07-19
Human level control through deep reinforcement learning✓ Link42.4Nature DQN2015-02-25
Asynchronous Methods for Deep Reinforcement Learning✓ Link41.8A3C LSTM hs2016-02-04
Policy Optimization With Penalized Point Probability Distance: An Alternative To Proximal Policy Optimization✓ Link38.99POP3D2018-07-02
[]()36.4SARSA
Asynchronous Methods for Deep Reinforcement Learning✓ Link36.2A3C FF (1 day) hs2016-02-04
Asynchronous Methods for Deep Reinforcement Learning✓ Link35.1A3C FF hs2016-02-04
Self-Imitation Learning✓ Link31.1A2C + SIL2018-06-14
Evolution Strategies as a Scalable Alternative to Reinforcement Learning✓ Link30ES FF (1 hour) noop2017-03-10
Distributed Prioritized Experience Replay✓ Link17.6Ape-X2018-03-02
Check out how to contribute new results.