Atari Games

Description from the archive archive 2025-07-28.

Benchmarks archive 2025-07-28

65 leaderboard tables shown for this task, 65 with rows (a “benchmark” on this site is a table with at least one row, as on /sota), ordered by row count. “Best model” is the first row in the archive's own order at snapshot; nothing is re-ranked here and metric direction is not recorded in the archive. PwC's Trend sparklines are not in the archive, so that column is omitted. 10 shown of 65 until expanded.

Syntology column: samples harvested from the paper's repositories and executed on synthesized fixtures; “ran” is not a correctness claim and does not order the table. A dash means no Syntology record for that paper, not a recorded non-run. Read from the graph 2026-09-24.

Libraries

Not in the archive: the export carries no per-task library table, so there is nothing to show at snapshot 2025-07-28.

Datasets archive 2025-07-28

6 datasets whose archive record lists this task, ordered by the archive's paper count.

Subtasks archive 2025-07-28

1 subtask in the archive's task tree.

Parent tasks archive 2025-07-28

Most implemented papers archive 2025-07-28

30 shown of 313 papers with code (625 tagged with this task in all), ordered by repositories listed in the archive, not by stars (the archive holds no stars, so PwC's “Social” and “Latest” sorts cannot be reproduced). Papers without a page here are shown as plain text.

• Playing Atari with Deep Reinforcement Learning
  19 Dec 2013 112 repositories listed Syntology ran 56 of 117 samples · 61 unverified · 56 pointer-only (licence)
  We present the first deep learning model to successfully learn control policies directly from high-dimensional sensory input using reinforcement learning.
• Deep Reinforcement Learning with Double Q-learning
  22 Sep 2015 97 repositories listed Syntology ran 55 of 106 samples · 51 unverified · 57 pointer-only (licence)
  The popular Q-learning algorithm is known to overestimate action values under certain conditions.
• Prioritized Experience Replay
  18 Nov 2015 77 repositories listed Syntology ran 78 of 111 samples · 33 unverified · 43 pointer-only (licence)
  Experience replay lets online reinforcement learning agents remember and reuse experiences from the past.
• Dueling Network Architectures for Deep Reinforcement Learning
  20 Nov 2015 73 repositories listed Syntology ran 5 of 11 samples · 6 unverified · 6 pointer-only (licence)
  In recent years there have been many successes of using deep representations in reinforcement learning.
• Asynchronous Methods for Deep Reinforcement Learning
  4 Feb 2016 70 repositories listed Syntology ran 38 of 95 samples · 57 unverified · 12 pointer-only (licence)
  We propose a conceptually simple and lightweight framework for deep reinforcement learning that uses asynchronous gradient descent for optimization of deep neural network controllers.
• Rainbow: Combining Improvements in Deep Reinforcement Learning
  6 Oct 2017 34 repositories listed Syntology ran 2 of 6 samples · 4 unverified · 1 pointer-only (licence)
  The deep reinforcement learning community has made several independent improvements to the DQN algorithm.
• Overcoming catastrophic forgetting in neural networks
  2 Dec 2016 29 repositories listed Syntology ran 14 of 22 samples · 8 unverified · 4 pointer-only (licence)
  The ability to learn tasks in a sequential fashion is crucial to the development of artificial intelligence.
• An Intriguing Failing of Convolutional Neural Networks and the CoordConv Solution
  9 Jul 2018 24 repositories listed Syntology ran 4 of 5 samples · 1 unverified
  In this paper we show a striking counterexample to this intuition via the seemingly trivial coordinate transform problem, which simply requires learning a mapping between coordinates in (x, y) Cartesian space and…
• IMPALA: Scalable Distributed Deep-RL with Importance Weighted Actor-Learner Architectures
  5 Feb 2018 24 repositories listed Syntology ran 16 of 34 samples · 18 unverified · 3 pointer-only (licence)
  In this work we aim to solve a large collection of tasks using a single reinforcement learning agent with a single set of parameters.
• Trust Region Policy Optimization
  19 Feb 2015 24 repositories listed Syntology ran 7 of 17 samples · 10 unverified · 7 pointer-only (licence)
  We describe an iterative procedure for optimizing policies, with guaranteed monotonic improvement.
• Evolution Strategies as a Scalable Alternative to Reinforcement Learning
  10 Mar 2017 23 repositories listed Syntology ran 7 of 29 samples · 22 unverified · 1 pointer-only (licence)
  We explore the use of Evolution Strategies (ES), a class of black box optimization algorithms, as an alternative to popular MDP-based RL techniques such as Q-learning and Policy Gradients.
• Exploration by Random Network Distillation
  30 Oct 2018 22 repositories listed Syntology ran 26 of 43 samples · 17 unverified · 15 pointer-only (licence)
  In particular we establish state of the art performance on Montezuma's Revenge, a game famously difficult for deep reinforcement learning methods.
• A Distributional Perspective on Reinforcement Learning
  21 Jul 2017 22 repositories listed Syntology ran 0 of 1 samples · 1 unverified · 1 pointer-only (licence)
  We obtain both state-of-the-art results and anecdotal evidence demonstrating the importance of the value distribution in approximate reinforcement learning.
• Decision Transformer: Reinforcement Learning via Sequence Modeling
  2 Jun 2021 20 repositories listed Syntology ran 17 of 26 samples · 9 unverified · 6 pointer-only (licence)
  In particular, we present Decision Transformer, an architecture that casts the problem of RL as conditional sequence modeling.
• Implicit Quantile Networks for Distributional Reinforcement Learning
  14 Jun 2018 19 repositories listed Syntology ran 0 of 2 samples · 2 unverified
  In this work, we build on recent advances in distributional reinforcement learning to give a generally applicable, flexible, and state-of-the-art distributional variant of DQN.
• Mastering Atari, Go, Chess and Shogi by Planning with a Learned Model
  19 Nov 2019 18 repositories listed Syntology ran 43 of 64 samples · 21 unverified · 62 pointer-only (licence)
  When evaluated on Go, chess and shogi, without any knowledge of the game rules, MuZero matched the superhuman performance of the AlphaZero algorithm that was supplied with the game rules.
• Distributional Reinforcement Learning with Quantile Regression
  27 Oct 2017 17 repositories listed Syntology ran 2 of 2 samples · 0 unverified · 1 pointer-only (licence)
  In this paper, we build on recent work advocating a distributional approach to reinforcement learning in which the distribution over returns is modeled explicitly instead of only estimating the mean.
• Distributed Prioritized Experience Replay
  2 Mar 2018 15 repositories listed Syntology ran 0 of 15 samples · 15 unverified
  We propose a distributed architecture for deep reinforcement learning at scale, that enables agents to learn effectively from orders of magnitude more data than previously possible.
• Noisy Networks for Exploration
  30 Jun 2017 15 repositories listed Syntology ran 1 of 3 samples · 2 unverified · 3 pointer-only (licence)
  We introduce NoisyNet, a deep reinforcement learning agent with parametric noise added to its weights, and show that the induced stochasticity of the agent's policy can be used to aid efficient exploration.
• Benchmarking Deep Reinforcement Learning for Continuous Control
  22 Apr 2016 15 repositories listed Syntology ran 0 of 4 samples · 4 unverified
  Recently, researchers have made significant progress combining the advances in deep learning for learning feature representations with reinforcement learning.
• Soft Actor-Critic for Discrete Action Settings
  16 Oct 2019 13 repositories listed Syntology ran 4 of 18 samples · 14 unverified · 3 pointer-only (licence)
  Soft Actor-Critic is a state-of-the-art reinforcement learning algorithm for continuous action settings that is not applicable to discrete action settings.
• ViZDoom: A Doom-based AI Research Platform for Visual Reinforcement Learning
  6 May 2016 10 repositories listed Syntology ran 2 of 5 samples · 3 unverified · 5 pointer-only (licence)
  Here, we propose a novel test-bed platform for reinforcement learning research from raw visual information which employs the first-person perspective in a semi-realistic 3D world.
• Mastering Atari with Discrete World Models
  5 Oct 2020 9 repositories listed Syntology ran 3 of 15 samples · 12 unverified
  The world model uses discrete representations and is trained separately from the policy.
• Accelerated Methods for Deep Reinforcement Learning
  7 Mar 2018 8 repositories listed Syntology ran 1 of 1 samples · 0 unverified · 1 pointer-only (licence)
  Deep reinforcement learning (RL) has achieved many recent successes, yet experiment turn-around time remains a key bottleneck in research and in practice.
• Scalable trust-region method for deep reinforcement learning using Kronecker-factored approximation
  17 Aug 2017 8 repositories listed Syntology ran 1 of 1 samples · 0 unverified
  In this work, we propose to apply trust region optimization to deep reinforcement learning using a recently proposed Kronecker-factored approximation to the curvature.
• Human level control through deep reinforcement learning
  25 Feb 2015 8 repositories listed
  We demonstrate that the deep Q-network agent, receiving only the pixels and the game score as inputs, was able to surpass the performance of all previous algorithms and achieve a level comparable to that of a…
• CURL: Contrastive Unsupervised Representations for Reinforcement Learning
  8 Apr 2020 7 repositories listed Syntology ran 6 of 8 samples · 2 unverified
  On the DeepMind Control Suite, CURL is the first image-based algorithm to nearly match the sample-efficiency of methods that use state-based features.
• Unsupervised State Representation Learning in Atari
  19 Jun 2019 7 repositories listed Syntology ran 3 of 10 samples · 7 unverified
  State representation learning, or the ability to capture latent generative factors of an environment, is crucial for building intelligent agents that can perform a wide variety of tasks.
• Fractal AI: A fragile theory of intelligence
  13 Mar 2018 7 repositories listed
  Fractal AI is a theory for general artificial intelligence.
• Revisiting the Arcade Learning Environment: Evaluation Protocols and Open Problems for General Agents
  18 Sep 2017 7 repositories listed
  The Arcade Learning Environment (ALE) is an evaluation platform that poses the challenge of building AI agents with general competency across dozens of Atari 2600 games.

Syntology lines on 27 of the papers shown; no Syntology record for the others (a paper without an arXiv id cannot be joined to the graph, and absence from the graph layer is not a recorded non-run). “Ran” means the sample executed on a synthesized fixture, not that the paper's result was reproduced. Read from the graph 2026-09-24.