Alternatives and similar repositories for retro:

Users that are interested in retro are comparing it to the libraries listed below

• Farama-Foundation / ViZDoom
  Reinforcement Learning environments based on the 1993 game Doom
  ☆1,747Updated 2 months ago
• Farama-Foundation / Arcade-Learning-Environment
  The Arcade Learning Environment (ALE) -- a platform for AI research.
  ☆2,189Updated this week
• rll / rllab
  rllab is a framework for developing and evaluating reinforcement learning algorithms, fully compatible with OpenAI Gym.
  ☆2,914Updated last year
• openai / mujoco-py
  MuJoCo is a physics engine for detailed, efficient rigid body simulations with contacts. mujoco-py allows using MuJoCo from Python 3.
  ☆2,887Updated 11 months ago
• openai / roboschool
  DEPRECATED: Open-source software for robot simulation, integrated with OpenAI Gym.
  ☆2,127Updated last year
• tensorforce / tensorforce
  Tensorforce: a TensorFlow library for applied reinforcement learning
  ☆3,297Updated 4 months ago
• openai / multiagent-competition
  Code for the paper "Emergent Complexity via Multi-agent Competition"
  ☆808Updated last year
• tensorflow / agents
  TF-Agents: A reliable, scalable and easy to use TensorFlow library for Contextual Bandits and Reinforcement Learning.
  ☆2,807Updated last month
• google-deepmind / trfl
  TensorFlow Reinforcement Learning
  ☆3,135Updated last year
• openai / procgen
  Procgen Benchmark: Procedurally-Generated Game-Like Gym-Environments
  ☆1,024Updated 10 months ago
• IntelLabs / coach
  Reinforcement Learning Coach by Intel AI Lab enables easy experimentation with state of the art Reinforcement Learning algorithms
  ☆2,331Updated last year
• openai / baselines
  OpenAI Baselines: high-quality implementations of reinforcement learning algorithms
  ☆15,844Updated 4 months ago
• geek-ai / MAgent
  A Platform for Many-Agent Reinforcement Learning
  ☆1,698Updated 2 years ago
• openai / spinningup
  An educational resource to help anyone learn deep reinforcement learning.
  ☆10,204Updated 3 months ago
• hill-a / stable-baselines
  A fork of OpenAI Baselines, implementations of reinforcement learning algorithms
  ☆4,169Updated 2 years ago
• openai / universe-starter-agent
  A starter agent that can solve a number of universe environments.
  ☆1,101Updated 6 years ago
• pathak22 / noreward-rl
  [ICML 2017] TensorFlow code for Curiosity-driven Exploration for Deep Reinforcement Learning
  ☆1,421Updated last year
• facebookresearch / ReAgent
  A platform for Reasoning systems (Reinforcement Learning, Contextual Bandits, etc.)
  ☆3,574Updated last week
• keras-rl / keras-rl
  Deep Reinforcement Learning for Keras.
  ☆5,529Updated last year
• Farama-Foundation / Minigrid
  Simple and easily configurable grid world environments for reinforcement learning
  ☆2,131Updated 2 weeks ago
• awjuliani / DeepRL-Agents
  A set of Deep Reinforcement Learning Agents implemented in Tensorflow.
  ☆2,241Updated 5 years ago
• openai / neural-mmo
  Code for the paper "Neural MMO: A Massively Multiagent Game Environment for Training and Evaluating Intelligent Agents"
  ☆1,587Updated last year
• google-deepmind / dm_control
  Google DeepMind's software stack for physics-based simulation and Reinforcement Learning environments, using MuJoCo.
  ☆3,828Updated last week
• openai / evolution-strategies-starter
  Code for the paper "Evolution Strategies as a Scalable Alternative to Reinforcement Learning"
  ☆1,567Updated 5 years ago
• google-deepmind / lab
  A customisable 3D platform for agent-based AI research
  ☆7,136Updated last year
• astooke / rlpyt
  Reinforcement Learning in PyTorch
  ☆2,233Updated 3 years ago
• rlworkgroup / garage
  A toolkit for reproducible reinforcement learning research.
  ☆1,887Updated last year
• google-deepmind / scalable_agent
  A TensorFlow implementation of Scalable Distributed Deep-RL with Importance Weighted Actor-Learner Architectures.
  ☆989Updated 5 years ago
• MultiAgentLearning / playground
  PlayGround: AI Research into Multi-Agent Learning.
  ☆767Updated 11 months ago
• google / dopamine
  Dopamine is a research framework for fast prototyping of reinforcement learning algorithms.
  ☆10,581Updated 3 weeks ago