google-deepmind / open_spielLinks
OpenSpiel is a collection of environments and algorithms for research in general reinforcement learning and search/planning in games.
☆4,614Updated this week
Alternatives and similar repositories for open_spiel
Users that are interested in open_spiel are comparing it to the libraries listed below
Sorting:
- An API standard for multi-agent reinforcement learning environments, with popular reference environments and related utilities☆3,008Updated last month
- Google DeepMind's software stack for physics-based simulation and Reinforcement Learning environments, using MuJoCo.☆4,136Updated 2 weeks ago
- bsuite is a collection of carefully-designed experiments that investigate core capabilities of a reinforcement learning (RL) agent☆1,524Updated last year
- A clean implementation based on AlphaZero for any game in any framework + tutorial + Othello/Gobang/TicTacToe/Connect4 and more☆4,187Updated 6 months ago
- The Arcade Learning Environment (ALE) -- a platform for AI research.☆2,308Updated 3 weeks ago
- Reinforcement Learning in PyTorch☆2,267Updated 4 years ago
- A platform for Reasoning systems (Reinforcement Learning, Contextual Bandits, etc.)☆3,636Updated last week
- TensorFlow Reinforcement Learning☆3,135Updated 2 years ago
- Simple and easily configurable grid world environments for reinforcement learning☆2,273Updated 3 weeks ago
- MuZero☆2,666Updated 10 months ago
- Pytorch Implementation of DQN / DDQN / Prioritized replay/ noisy networks/ distributional values/ Rainbow/ hierarchical RL☆3,113Updated 3 years ago
- TF-Agents: A reliable, scalable and easy to use TensorFlow library for Contextual Bandits and Reinforcement Learning.☆2,928Updated 3 weeks ago
- A library of reinforcement learning components and agents☆3,722Updated last month
- Reinforcement Learning Coach by Intel AI Lab enables easy experimentation with state of the art Reinforcement Learning algorithms☆2,348Updated 2 years ago
- Environment generation code for the paper "Emergent Tool Use From Multi-Agent Autocurricula"☆1,719Updated 11 months ago
- Rainbow: Combining Improvements in Deep Reinforcement Learning☆1,633Updated 3 years ago
- A toolkit for reproducible reinforcement learning research.☆1,993Updated 2 years ago
- MuJoCo is a physics engine for detailed, efficient rigid body simulations with contacts. mujoco-py allows using MuJoCo from Python 3.☆3,020Updated last year
- SEED RL: Scalable and Efficient Deep-RL with Accelerated Central Inference. Implements IMPALA and R2D2 algorithms in TF2 with SEED's arch…☆825Updated 2 years ago
- Implementations of basic RL algorithms with minimal lines of codes! (pytorch based)☆3,026Updated 2 years ago
- A Platform for Many-Agent Reinforcement Learning☆1,743Updated 2 years ago
- Code for the paper "Large-Scale Study of Curiosity-Driven Learning"☆819Updated 3 years ago
- rllab is a framework for developing and evaluating reinforcement learning algorithms, fully compatible with OpenAI Gym.☆2,978Updated 2 years ago
- An algorithm that generalizes the paradigm of self-play reinforcement learning and search to imperfect-information games.☆680Updated last year
- Code for a multi-agent particle environment used in the paper "Multi-Agent Actor-Critic for Mixed Cooperative-Competitive Environments"☆2,596Updated last year
- hanabi_learning_environment is a research platform for Hanabi experiments.☆653Updated 2 years ago
- ChainerRL is a deep reinforcement learning library built on top of Chainer.☆1,195Updated 3 years ago
- Retro Games in Gym☆3,508Updated last year
- Learning Latent Dynamics for Planning from Pixels☆1,198Updated 2 years ago
- A fork of OpenAI Baselines, implementations of reinforcement learning algorithms☆4,297Updated 2 years ago