Datasets › Arcade Learning Environment

Arcade Learning Environment

Introduced by Marc G. Bellemare et al. in The Arcade Learning Environment: An Evaluation Platform for General Agents1 Jan 2012 archive 2025-07-28

The Arcade Learning Environment (ALE) is an object-oriented framework that allows researchers to develop AI agents for Atari 2600 games. It is built on top of the Atari 2600 emulator Stella and separates the details of emulation from agent design.

Source: https://github.com/mgbellemare/Arcade-Learning-Environment Image Source: https://github.com/muupan/async-rl/blob/master/README.md

Benchmarks archive 2025-07-28

All 57 leaderboards whose dataset resolves to this page shown (sort by any header). "First row" is the archive's own first row at snapshot, in the archive's row order; nothing here re-ranks and metric direction is not asserted.

First row (archive order)PaperCode
Atari Games Atari 2600 Freeway TRPO-hash Score 34.0 #Exploration: A Study of Count-Based Exploration for... uoe-agents/derl +2 59 Compare
Atari Games Atari 2600 Breakout GDI-H3(200M frames) Score 864.00 Generalized Data Distribution Iteration — 58 Compare
Atari Games Atari 2600 Q*Bert Agent57 Score 580328.14 Agent57: Outperforming the Atari Human Benchmark michaelnny/deep_rl_zoo +4 57 Compare
Atari Games Atari 2600 Seaquest GDI-H3(200M frames) Score 1000000 Generalized Data Distribution Iteration — 57 Compare
Atari Games Atari 2600 Space Invaders GDI-H3(200M frames) Score 154380 Generalized Data Distribution Iteration — 55 Compare
Atari Games Atari 2600 Venture Agent57 Score 2623.71 Agent57: Outperforming the Atari Human Benchmark michaelnny/deep_rl_zoo +4 55 Compare
Atari Games Atari 2600 Frostbite MuZero Score 631378.53 Mastering Atari, Go, Chess and Shogi by Planning with a... werner-duvaud/muzero-general +17 53 Compare
Atari Games Atari 2600 Gravitar Agent57 Score 19213.96 Agent57: Outperforming the Atari Human Benchmark michaelnny/deep_rl_zoo +4 53 Compare
Atari Games Atari 2600 Pong Duel noop Score 21.0 Dueling Network Architectures for Deep Reinforcement Learning labmlai/annotated_deep_learning_paper_implementations +72 52 Compare
Atari Games Atari 2600 Private Eye Go-Explore Score 95756 First return, then explore uber-research/go-explore +1 52 Compare
Atari Games Atari 2600 Montezuma's Revenge Go-Explore Score 43791 First return, then explore uber-research/go-explore +1 50 Compare
Atari Games Atari 2600 Alien MuZero Score 741812.63 Mastering Atari, Go, Chess and Shogi by Planning with a... werner-duvaud/muzero-general +17 49 Compare
Atari Games Atari 2600 Beam Rider MuZero Score 454993.53 Mastering Atari, Go, Chess and Shogi by Planning with a... werner-duvaud/muzero-general +17 49 Compare
Atari Games Atari 2600 Crazy Climber Agent57 Score 565909.85 Agent57: Outperforming the Atari Human Benchmark michaelnny/deep_rl_zoo +4 49 Compare
Atari Games Atari 2600 Amidar Agent57 Score 29660.08 Agent57: Outperforming the Atari Human Benchmark michaelnny/deep_rl_zoo +4 48 Compare
Atari Games Atari 2600 Battle Zone Agent57 Score 934134.88 Agent57: Outperforming the Atari Human Benchmark michaelnny/deep_rl_zoo +4 47 Compare
Atari Games Atari 2600 Kangaroo Agent57 Score 24034.16 Agent57: Outperforming the Atari Human Benchmark michaelnny/deep_rl_zoo +4 47 Compare
Atari Games Atari 2600 Ms. Pacman MuZero Score 243401.10 Mastering Atari, Go, Chess and Shogi by Planning with a... werner-duvaud/muzero-general +17 47 Compare
Atari Games Atari 2600 Demon Attack GDI-H3 Score 787985 Generalized Data Distribution Iteration — 46 Compare
Atari Games Atari 2600 Assault MuZero Score 143972.03 Mastering Atari, Go, Chess and Shogi by Planning with a... werner-duvaud/muzero-general +17 45 Compare
Atari Games Atari 2600 Bank Heist MuZero (Res2 Adam) Score 27219.8 Online and Offline Reinforcement Learning by Planning... DHDev0/Muzero-unplugged +1 45 Compare
Atari Games Atari 2600 Centipede Go-Explore Score 1422628 First return, then explore uber-research/go-explore +1 45 Compare
Atari Games Atari 2600 Chopper Command GDI-H3 Score 999999 GDI: Rethinking What Makes Reinforcement Learning... — 45 Compare
Atari Games Atari 2600 James Bond GDI-H3 Score 620780 Generalized Data Distribution Iteration — 45 Compare
Atari Games Atari 2600 Krull GDI-H3 Score 594540 Generalized Data Distribution Iteration — 45 Compare
Atari Games Atari 2600 Bowling MuZero Score 260.13 Mastering Atari, Go, Chess and Shogi by Planning with a... werner-duvaud/muzero-general +17 44 Compare
Atari Games Atari 2600 Fishing Derby MuZero Score 91.16 Mastering Atari, Go, Chess and Shogi by Planning with a... werner-duvaud/muzero-general +17 44 Compare
Atari Games Atari 2600 HERO Agent57 Score 114736.26 Agent57: Outperforming the Atari Human Benchmark michaelnny/deep_rl_zoo +4 44 Compare
Atari Games Atari 2600 Road Runner GDI-H3 Score 999999 Generalized Data Distribution Iteration — 44 Compare
Atari Games Atari 2600 Time Pilot MuZero Score 476763.90 Mastering Atari, Go, Chess and Shogi by Planning with a... werner-duvaud/muzero-general +17 44 Compare
Atari Games Atari 2600 Tutankham Agent57 Score 2354.91 Agent57: Outperforming the Atari Human Benchmark michaelnny/deep_rl_zoo +4 44 Compare
Atari Games Atari 2600 Up and Down GDI-I3 Score 986440 GDI: Rethinking What Makes Reinforcement Learning... — 44 Compare
Atari Games Atari 2600 Asteroids GDI-H3 Score 760005 Generalized Data Distribution Iteration — 43 Compare
Atari Games Atari 2600 Double Dunk UCT Score 24 The Arcade Learning Environment: An Evaluation Platform... mgbellemare/Arcade-Learning-Environment +2 43 Compare
Atari Games Atari 2600 Gopher GDI-I3 Score 488830 Generalized Data Distribution Iteration — 43 Compare
Atari Games Atari 2600 Ice Hockey GDI-H3 Score 481.9 Generalized Data Distribution Iteration — 43 Compare
Atari Games Atari 2600 Kung-Fu Master GDI-H3 Score 1666665 Generalized Data Distribution Iteration — 43 Compare
Atari Games Atari 2600 Name This Game MuZero Score 157177.85 Mastering Atari, Go, Chess and Shogi by Planning with a... werner-duvaud/muzero-general +17 43 Compare
Atari Games Atari 2600 Tennis GDI-I3 Score 24 GDI: Rethinking What Makes Reinforcement Learning... — 43 Compare
Atari Games Atari 2600 Atlantis GDI-H3 Score 3837300 Generalized Data Distribution Iteration — 42 Compare
Atari Games Atari 2600 Robotank MuZero Score 131.13 Mastering Atari, Go, Chess and Shogi by Planning with a... werner-duvaud/muzero-general +17 42 Compare
Atari Games Atari 2600 Video Pinball R2D2 Score 999383.2 Recurrent Experience Replay in Distributed Reinforcement Learning opendilab/DI-engine +2 42 Compare
Atari Games Atari 2600 River Raid MuZero Score 323417.18 Mastering Atari, Go, Chess and Shogi by Planning with a... werner-duvaud/muzero-general +17 41 Compare
Atari Games Atari 2600 Wizard of Wor MuZero Score 197126.00 Mastering Atari, Go, Chess and Shogi by Planning with a... werner-duvaud/muzero-general +17 41 Compare
Atari Games Atari 2600 Zaxxon MuZero Score 725853.90 Mastering Atari, Go, Chess and Shogi by Planning with a... werner-duvaud/muzero-general +17 41 Compare
Atari Games Atari 2600 Berzerk Go-Explore Score 197376 First return, then explore uber-research/go-explore +1 39 Compare
Atari Games Atari 2600 Pitfall! Go-Explore Score 102571 Go-Explore: a New Approach for Hard-Exploration Problems uber-research/go-explore +2 23 Compare
Atari Games Atari 2600 Skiing Best Learner Score 0 The Arcade Learning Environment: An Evaluation Platform... mgbellemare/Arcade-Learning-Environment +2 23 Compare
Atari Games Atari 2600 Phoenix GDI-H3 Score 959580 Generalized Data Distribution Iteration — 21 Compare
Atari Games Atari 2600 Yars Revenge Agent57 Score 998532.37 Agent57: Outperforming the Atari Human Benchmark michaelnny/deep_rl_zoo +4 17 Compare
Atari Games Atari 2600 Surround NoisyNet-Dueling Score 10 Noisy Networks for Exploration opendilab/DI-engine +14 15 Compare
Atari Games Atari-57 LBC Mean Human Normalized Score 10077.52% Learnable Behavior Control: Breaking Atari Human World... — 11 Compare
Atari Games Atari 2600 Elevator Action Persistent AL Score 29100 Increasing the Action Gap: New Operators for... janhuenermann/neurojs +1 3 Compare
Atari Games Atari 2600 Pooyan UCT Score 17763.4 The Arcade Learning Environment: An Evaluation Platform... mgbellemare/Arcade-Learning-Environment +2 3 Compare
Montezuma's Revenge Atari 2600 Montezuma's Revenge Flare Average Return (NoOp) 1668 Reinforcement Learning with Latent Flow WendyShang/flare +1 3 Compare
Atari Games Atari 2600 Carnival UCT Score 5132.0 The Arcade Learning Environment: An Evaluation Platform... mgbellemare/Arcade-Learning-Environment +2 1 Compare
Atari Games Atari 2600 Journey Escape UCT Score 7683.3 The Arcade Learning Environment: An Evaluation Platform... mgbellemare/Arcade-Learning-Environment +2 1 Compare

Papers archive 2025-07-28

papers with a benchmark row: 66 · with a code link: 56 · where Syntology ran a sample: 35 (26 with a run with no instrument failure, 9 where every run was a failure of Syntology's instrument) Syntology

Show: all papers with a benchmark rowonly where code ran (35 of 66 with a benchmark row: 26 with a run with no instrument failure, 9 where every run was a failure of Syntology's instrument)

Page 1 of 1: papers 1 to 66 of 66 with a leaderboard row on this dataset's benchmarks, newest first by the archive's date (ties by slug; undated papers last).

The archive's own "papers using this dataset" list was never published, so this is the benchmark-backed subset, not that list; the archive's count for this dataset is 366. The Syntology column is from Syntology's graph, stated per sample; it is not part of any archive number. A line reads “N ran (of which C constructed an object rather than computing a result; K with no instrument failure: H honoured, V violated, P with no contract checked; I where Syntology's instrument failed) · U unverified” (C is a part of N, never taken away from it); the figure “where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code. “Ran” means the sample executed on a synthesized fixture, not that the paper's result was reproduced. When the archive marks a repository official for the paper, the cell starts with that repository's state (the archive's flag, not a verdict on who wrote the code; “community repositories only” when every sample that ran came from a community repository, “official: no sample here; runs from other or unrecorded repositories” when some came from a repository the paper names or has in its text, or from none recorded); hover it for the repositories the samples that ran came from. Syntology's record for this page last changed ; when this build read Syntology's graph is in the build record.

PaperCodeResultsDateSamples run Syntology
Learnable Behavior Control: Breaking Atari Human World Records via Sample-Efficient Behavior Selection 0 1 9 May 2023 not harvested
Train a Real-world Local Path Planner in One Hour via Partially Decoupled Reinforcement Learning and Vectorized Diversity 1 51 7 May 2023 not harvested
Self-supervised network distillation: an effective approach to exploration in sparse reward environments 2 14 22 Feb 2023 not harvested
DNA: Proximal Policy Optimization with a Dual Network Architecture 1 51 20 Jun 2022 not harvested
Generalized Data Distribution Iteration 0 114 7 Jun 2022 not harvested
GDI: Rethinking What Makes Reinforcement Learning Different from Supervised Learning 0 3 24 Nov 2021 not harvested
IQ-Learn: Inverse soft-Q Learning for Imitation 5 4 23 Jun 2021 community repositories only · 2 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 2 where Syntology's instrument failed) · 1 unverified (3 pointer-only for licence)
GDI: Rethinking What Makes Reinforcement Learning Different From Supervised Learning 0 36 11 Jun 2021 not harvested
Decision Transformer: Reinforcement Learning via Sequence Modeling 20 4 2 Jun 2021 community repositories only · 17 ran (of which 10 constructed an object rather than computing a result; 12 with no instrument failure: 0 honoured, 0 violated, 12 with no contract checked; 5 where Syntology's instrument failed) · 9 unverified (8 pointer-only for licence)
Online and Offline Reinforcement Learning by Planning with a Learned Model 2 51 13 Apr 2021 not harvested
Improving Computational Efficiency in Visual Reinforcement Learning via Stored Embeddings 1 8 4 Mar 2021 not harvested
Adaptive Rational Activations to Boost Deep Reinforcement Learning 4 26 18 Feb 2021 official (archive's flag): 6 ran · 6 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 6 where Syntology's instrument failed) · 0 unverified (3 pointer-only for licence)
Reinforcement Learning with Latent Flow 2 2 6 Jan 2021 official (archive's flag): 1 ran · 1 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified
Optimizing the Neural Architecture of Reinforcement Learning Agents 1 6 30 Nov 2020 not harvested
Smaller World Models for Reinforcement Learning 0 6 12 Oct 2020 not harvested
Mastering Atari with Discrete World Models 9 50 5 Oct 2020 community repositories only · 11 ran (of which 1 constructed an object rather than computing a result; 10 with no instrument failure: 0 honoured, 1 violated, 9 with no contract checked; 1 where Syntology's instrument failed) · 4 unverified
Model-Free Episodic Control with State Aggregation 0 6 21 Aug 2020 not harvested
Munchausen Reinforcement Learning 6 1 28 Jul 2020 community repositories only · 12 ran (of which 11 constructed an object rather than computing a result; 12 with no instrument failure: 0 honoured, 1 violated, 11 with no contract checked; 0 where Syntology's instrument failed) · 10 unverified
First return, then explore 2 10 27 Apr 2020 official (archive's flag): 2 ran · 2 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 1 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 2 unverified (4 pointer-only for licence)
CURL: Contrastive Unsupervised Representations for Reinforcement Learning 7 24 8 Apr 2020 official (archive's flag): 6 ran · 7 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 0 violated, 2 with no contract checked; 5 where Syntology's instrument failed) · 1 unverified (3 pointer-only for licence)
Agent57: Outperforming the Atari Human Benchmark 5 51 30 Mar 2020 8 ran (of which 0 constructed an object rather than computing a result; 8 with no instrument failure: 0 honoured, 0 violated, 8 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified
Mastering Atari, Go, Chess and Shogi by Planning with a Learned Model 18 51 19 Nov 2019 43 ran (of which 36 constructed an object rather than computing a result; 43 with no instrument failure: 4 honoured, 0 violated, 39 with no contract checked; 0 where Syntology's instrument failed) · 21 unverified (62 pointer-only for licence)
Fully Parameterized Quantile Function for Distributional Reinforcement Learning 6 23 5 Nov 2019 6 ran (of which 0 constructed an object rather than computing a result; 5 with no instrument failure: 0 honoured, 0 violated, 5 with no contract checked; 1 where Syntology's instrument failed) · 4 unverified
Soft Actor-Critic for Discrete Action Settings 13 18 16 Oct 2019 official: harvested, nothing ran · 12 ran (of which 0 constructed an object rather than computing a result; 12 with no instrument failure: 2 honoured, 1 violated, 9 with no contract checked; 0 where Syntology's instrument failed) · 6 unverified (3 pointer-only for licence)
Off-Policy Actor-Critic with Shared Experience Replay 0 1 25 Sep 2019 not harvested
Recurrent Independent Mechanisms 3 3 24 Sep 2019 14 ran (of which 9 constructed an object rather than computing a result; 14 with no instrument failure: 1 honoured, 0 violated, 13 with no contract checked; 0 where Syntology's instrument failed) · 6 unverified (20 pointer-only for licence)
Recurrent Experience Replay in Distributed Reinforcement Learning 3 52 1 May 2019 not harvested
Go-Explore: a New Approach for Hard-Exploration Problems 3 2 30 Jan 2019 2 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 1 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 2 unverified (4 pointer-only for licence)
Contingency-Aware Exploration in Reinforcement Learning 0 1 5 Nov 2018 not harvested
Exploration by Random Network Distillation 22 5 30 Oct 2018 community repositories only · 31 ran (of which 12 constructed an object rather than computing a result; 24 with no instrument failure: 2 honoured, 1 violated, 21 with no contract checked; 7 where Syntology's instrument failed) · 12 unverified (16 pointer-only for licence)
Large-Scale Study of Curiosity-Driven Learning 5 5 13 Aug 2018 community repositories only · 3 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 3 where Syntology's instrument failed) · 0 unverified (3 pointer-only for licence)
Count-Based Exploration with the Successor Representation 2 6 31 Jul 2018 official (archive's flag): 1 ran · 1 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified
Policy Optimization With Penalized Point Probability Distance: An Alternative To Proximal Policy Optimization 2 45 2 Jul 2018 not harvested
RUDDER: Return Decomposition for Delayed Rewards 2 3 20 Jun 2018 official (archive's flag): 7 ran · 7 ran (of which 0 constructed an object rather than computing a result; 5 with no instrument failure: 0 honoured, 1 violated, 4 with no contract checked; 2 where Syntology's instrument failed) · 2 unverified (9 pointer-only for licence)
Evolving simple programs for playing Atari games 2 50 14 Jun 2018 7 ran (of which 0 constructed an object rather than computing a result; 7 with no instrument failure: 0 honoured, 0 violated, 7 with no contract checked; 0 where Syntology's instrument failed) · 2 unverified
Implicit Quantile Networks for Distributional Reinforcement Learning 19 51 14 Jun 2018 2 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 0 violated, 2 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified
Self-Imitation Learning 4 45 14 Jun 2018 community repositories only · 3 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 0 violated, 2 with no contract checked; 1 where Syntology's instrument failed) · 3 unverified (3 pointer-only for licence)
Playing Atari with Six Neurons 1 10 4 Jun 2018 not harvested
Distributed Prioritized Experience Replay 15 51 2 Mar 2018 9 ran (of which 0 constructed an object rather than computing a result; 9 with no instrument failure: 0 honoured, 0 violated, 9 with no contract checked; 0 where Syntology's instrument failed) · 6 unverified (3 pointer-only for licence)
IMPALA: Scalable Distributed Deep-RL with Importance Weighted Actor-Learner Architectures 24 52 5 Feb 2018 community repositories only · 16 ran (of which 6 constructed an object rather than computing a result; 10 with no instrument failure: 1 honoured, 1 violated, 8 with no contract checked; 6 where Syntology's instrument failed) · 18 unverified (3 pointer-only for licence)
Distributed Deep Reinforcement Learning: Learn how to play Atari games in 21 minutes 1 5 9 Jan 2018 not harvested
Distributional Reinforcement Learning with Quantile Regression 17 51 27 Oct 2017 2 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 2 where Syntology's instrument failed) · 0 unverified (2 pointer-only for licence)
Rainbow: Combining Improvements in Deep Reinforcement Learning 34 4 6 Oct 2017 5 ran (of which 0 constructed an object rather than computing a result; 5 with no instrument failure: 1 honoured, 1 violated, 3 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified (1 pointer-only for licence)
Mean Actor Critic 2 6 1 Sep 2017 not harvested
A Distributional Perspective on Reinforcement Learning 22 45 21 Jul 2017 0 ran · 1 unverified (1 pointer-only for licence)
Value Prediction Network 2 8 11 Jul 2017 not harvested
Noisy Networks for Exploration 15 48 30 Jun 2017 1 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 2 unverified (3 pointer-only for licence)
Count-Based Exploration in Feature Space for Reinforcement Learning 1 10 25 Jun 2017 not harvested
The Reactor: A fast and sample-efficient Actor-Critic agent for Reinforcement Learning 0 16 15 Apr 2017 not harvested
Evolution Strategies as a Scalable Alternative to Reinforcement Learning 23 41 10 Mar 2017 official (archive's flag): 4 ran · 16 ran (of which 0 constructed an object rather than computing a result; 11 with no instrument failure: 0 honoured, 1 violated, 10 with no contract checked; 5 where Syntology's instrument failed) · 13 unverified (2 pointer-only for licence)
Count-Based Exploration with Neural Density Models 1 9 3 Mar 2017 1 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified
#Exploration: A Study of Count-Based Exploration for Deep Reinforcement Learning 3 4 15 Nov 2016 not harvested
Unifying Count-Based Exploration and Intrinsic Motivation 1 6 6 Jun 2016 not harvested
Learning values across many orders of magnitude 0 45 24 Feb 2016 not harvested
Deep Exploration via Bootstrapped DQN 6 45 15 Feb 2016 1 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 1 unverified (2 pointer-only for licence)
Asynchronous Methods for Deep Reinforcement Learning 70 138 4 Feb 2016 60 ran (of which 20 constructed an object rather than computing a result; 50 with no instrument failure: 2 honoured, 1 violated, 47 with no contract checked; 10 where Syntology's instrument failed) · 35 unverified (20 pointer-only for licence)
Increasing the Action Gap: New Operators for Reinforcement Learning 2 88 15 Dec 2015 not harvested
Deep Attention Recurrent Q-Network 3 5 5 Dec 2015 not harvested
Dueling Network Architectures for Deep Reinforcement Learning 73 185 20 Nov 2015 7 ran (of which 0 constructed an object rather than computing a result; 5 with no instrument failure: 3 honoured, 0 violated, 2 with no contract checked; 2 where Syntology's instrument failed) · 4 unverified (7 pointer-only for licence)
Prioritized Experience Replay 77 91 18 Nov 2015 80 ran (of which 62 constructed an object rather than computing a result; 72 with no instrument failure: 4 honoured, 0 violated, 68 with no contract checked; 8 where Syntology's instrument failed) · 31 unverified (43 pointer-only for licence)
Deep Reinforcement Learning with Double Q-learning 97 183 22 Sep 2015 56 ran (of which 38 constructed an object rather than computing a result; 55 with no instrument failure: 0 honoured, 0 violated, 55 with no contract checked; 1 where Syntology's instrument failed) · 50 unverified (57 pointer-only for licence)
Massively Parallel Methods for Deep Reinforcement Learning 3 45 15 Jul 2015 not harvested
Incentivizing Exploration In Reinforcement Learning With Deep Predictive Models 1 5 3 Jul 2015 not harvested
Human level control through deep reinforcement learning 8 45 25 Feb 2015 not harvested
Playing Atari with Deep Reinforcement Learning 112 6 19 Dec 2013 64 ran (of which 24 constructed an object rather than computing a result; 46 with no instrument failure: 5 honoured, 0 violated, 41 with no contract checked; 18 where Syntology's instrument failed) · 53 unverified (56 pointer-only for licence)
The Arcade Learning Environment: An Evaluation Platform for General Agents 3 98 19 Jul 2012 2 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 2 where Syntology's instrument failed) · 0 unverified (2 pointer-only for licence)

Dataset loaders archive 2025-07-28

1 loader as listed in the archive; links are outbound and not re-checked here.

Tasks archive 2025-07-28

License archive 2025-07-28

GPL-2

Modalities archive 2025-07-28

Languages archive 2025-07-28

No language tagged.

Variants archive 2025-07-28

  • Atari 2600 Breakout
  • Arcade Learning Environment
  • Atari 2600 Yars Revenge
  • Atari 2600 Wizard of Wor
  • Atari 2600 Video Pinball
  • Atari 2600 Up and Down
  • Atari 2600 Tutankham
  • Atari 2600 Time Pilot
  • Atari 2600 Surround
  • Atari 2600 Space Invaders
  • Atari 2600 Seaquest
  • Atari 2600 Robotank
  • Atari 2600 Road Runner
  • Atari 2600 River Raid
  • Atari 2600 Private Eye
  • Atari 2600 Pitfall!
  • Atari 2600 Name This Game
  • Atari 2600 Ms. Pacman
  • Atari 2600 Montezuma's Revenge
  • Atari 2600 Kung-Fu Master
  • Atari 2600 Kangaroo
  • Atari 2600 Journey Escape
  • Atari 2600 James Bond
  • Atari 2600 Ice Hockey
  • Atari 2600 Gravitar
  • Atari 2600 Frostbite
  • Atari 2600 Freeway
  • Atari 2600 Fishing Derby
  • Atari 2600 Elevator Action
  • Atari 2600 Double Dunk
  • Atari 2600 Demon Attack
  • Atari 2600 Crazy Climber
  • Atari 2600 Chopper Command
  • Atari 2600 Centipede
  • Atari 2600 Carnival
  • Atari 2600 Beam Rider
  • Atari 2600 Battle Zone
  • Atari 2600 Bank Heist
  • Atari 2600 Atlantis
  • Atari 2600 Asteroids
  • Atari 2600 Assault
  • Atari-57
  • Atari 2600 Zaxxon
  • Atari 2600 Venture
  • Atari 2600 Tennis
  • Atari 2600 Skiing
  • Atari 2600 Q*Bert
  • Atari 2600 Pooyan
  • Atari 2600 Pong
  • Atari 2600 Phoenix
  • Atari 2600 Krull
  • Atari 2600 HERO
  • Atari 2600 Gopher
  • Atari 2600 Bowling
  • Atari 2600 Berzerk
  • Atari 2600 Amidar
  • Atari 2600 Alien

57 variant names, as the archive lists them.

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections