Datasets › OpenAI Gym

OpenAI Gym

Introduced by Greg Brockman et al. in OpenAI Gym1 Jan 2016 archive 2025-07-28

OpenAI Gym is a toolkit for developing and comparing reinforcement learning algorithms. It includes environment such as Algorithmic, Atari, Box2D, Classic Control, MuJoCo, Robotics, and Toy Text.

Source: https://github.com/openai/gym Image Source: https://medium.com/@tuzzer/cart-pole-balancing-with-q-learning-b54c6068d947

Benchmarks archive 2025-07-28

All 3 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
Continuous Control Lunar Lander (OpenAI Gym) SAC Score 284.59±0.97 Soft Actor-Critic: Off-Policy Maximum Entropy Deep... ray-project/ray +85 5 Compare
OpenAI Gym Pendulum-v1 TLA with Hierarchical Reward Functions Mean Reward -125.02 Creating Hierarchical Dispositions of Needs in an Agent TofaraMoyo/Heirachical-Reward-Functions 2 Compare
Continuous Control Cart Pole (OpenAI Gym) MAC Score 178.3 Mean Actor Critic kavosh8/MAC +1 1 Compare

Papers archive 2025-07-28

7 shown of 7 papers with a leaderboard row on this dataset's benchmarks, newest first. The archive's own "papers using this dataset" list was never published, so this is the benchmark-backed subset; the archive's count for this dataset is 1,305. The Syntology column is from Syntology's graph (read 2026-09-24), stated per sample; it is not part of any archive number.

DateSamples run Syntology
Creating Hierarchical Dispositions of Needs in an Agent 1 1 23 Nov 2024 not harvested
Optimizing Attention and Cognitive Control Costs Using Temporally-Layered Architectures 1 1 30 May 2023 not harvested
Addressing Function Approximation Error in Actor-Critic Methods 67 1 26 Feb 2018 ran 9 of 36 samples (27 unverified; 20 pointer-only for licence)
Soft Actor-Critic: Off-Policy Maximum Entropy Deep Reinforcement Learning with a Stochastic Actor 86 1 4 Jan 2018 ran 91 of 148 samples (57 unverified; 66 pointer-only for licence)
Mean Actor Critic 2 2 1 Sep 2017 not harvested
Proximal Policy Optimization Algorithms 188 1 20 Jul 2017 ran 99 of 176 samples (77 unverified; 94 pointer-only for licence)
Continuous control with deep reinforcement learning 161 1 9 Sep 2015 ran 158 of 306 samples (148 unverified; 163 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

MIT

Modalities archive 2025-07-28

Languages archive 2025-07-28

Variants archive 2025-07-28

  • OpenAI Gym
  • Cart Pole (OpenAI Gym)
  • Lunar Lander (OpenAI Gym)
  • Pendulum-v1

4 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