OpenAI Gym
A standard library of reinforcement learning environments developed by OpenAI. It provides simulation environments for games and control tasks, and has become the dominant ecosystem for reinforcement learning research and development.
Core Facts
Gymnasium, maintained by the Farama Foundation, succeeded OpenAI Gym and defines the environment interface standard
OpenAI Gym was released in 2016 and became the de facto standard environment interface in the field of reinforcement learning.
Timeline (last 90 days)
OpenAI Gym has been renamed to Gymnasium.
Gymnasium (formerly OpenAI Gym) provides an environment interface convention that allows simulation environments and real robots to share the same definition of observation and action spaces.
OpenAI Gym (now Gymnasium) and PettingZoo can be used to hands-on implement classic reinforcement learning environments such as mazes and CartPole.
CartPole is the most classic introductory reinforcement learning environment in OpenAI Gym, with a 4-dimensional state and 2 actions, and typically a few hundred lines of code and a few dozen seconds are enough to train a stable policy.
MuJoCo has become one of the core simulation backends in the OpenAI Gym / Gymnasium ecosystem.
OpenAI Gym wraps MuJoCo environments into a unified step/reset/render interface, making it the de facto standard testing platform for reinforcement learning algorithms.
Bot-friendly reinforcement learning environments typically follow standard interface specifications similar to OpenAI Gym/Gymnasium, providing standard methods such as observation, action, reward, and step/reset
OpenAI's Gym, DeepMind's Atari challenge, and Pokémon-series reinforcement learning experiments have long served as testing grounds in the field of reinforcement learning
MuJoCo is the default physics backend for classic control tasks in OpenAI Gym/Gymnasium.
Gym由OpenAI于2016年4月发布
7 more timeline events
All Facts (18)
Gymnasium, maintained by the Farama Foundation, succeeded OpenAI Gym and defines the environment interface standard
70%VerifiedOpenAI Gym was released in 2016 and became the de facto standard environment interface in the field of reinforcement learning.
65%UnverifiedPyBullet is a Python wrapper for the Bullet physics engine, lightweight and easy to use, commonly used for teaching and rapid prototype development.
60%UnverifiedOpenAI Gym provides a standardized environment interface, but its officially built-in environments are almost exclusively Atari games and MuJoCo physics simulations.
60%UnverifiedOpenAI Gym has been renamed to Gymnasium.
50%UnverifiedGymnasium (formerly OpenAI Gym) provides an environment interface convention that allows simulation environments and real robots to share the same definition of observation and action spaces.
50%UnverifiedOpenAI Gym (now Gymnasium) and PettingZoo can be used to hands-on implement classic reinforcement learning environments such as mazes and CartPole.
50%UnverifiedCartPole is the most classic introductory reinforcement learning environment in OpenAI Gym, with a 4-dimensional state and 2 actions, and typically a few hundred lines of code and a few dozen seconds are enough to train a stable policy.
50%UnverifiedMuJoCo has become one of the core simulation backends in the OpenAI Gym / Gymnasium ecosystem.
50%UnverifiedOpenAI Gym wraps MuJoCo environments into a unified step/reset/render interface, making it the de facto standard testing platform for reinforcement learning algorithms.
50%UnverifiedBot-friendly reinforcement learning environments typically follow standard interface specifications similar to OpenAI Gym/Gymnasium, providing standard methods such as observation, action, reward, and step/reset
50%UnverifiedOpenAI's Gym, DeepMind's Atari challenge, and Pokémon-series reinforcement learning experiments have long served as testing grounds in the field of reinforcement learning
50%UnverifiedMuJoCo is the default physics backend for classic control tasks in OpenAI Gym/Gymnasium.
50%UnverifiedGym由OpenAI于2016年4月发布
50%UnverifiedOpenAI Gym通过env.reset()、env.step(action)、env.render()等标准方法与环境交互
50%UnverifiedCarRacing是OpenAI Gym中的连续控制任务，输入为96×96的RGB像素图像，输出为转向、油门和刹车的连续动作
50%UnverifiedGymnasium是OpenAI Gym的社区维护后继版本，已成为强化学习环境的事实标准接口
50%UnverifiedOpenAI Gym 中的 LunarLander、BipedalWalker 等经典环境都基于 Box2D 构建
50%