google-deepmind / open_spiel
OpenSpiel is a collection of environments and algorithms for research in general reinforcement learning and search/planning in games.
☆4,381Updated this week
Alternatives and similar repositories for open_spiel:
Users that are interested in open_spiel are comparing it to the libraries listed below
- bsuite is a collection of carefully-designed experiments that investigate core capabilities of a reinforcement learning (RL) agent☆1,518Updated 10 months ago
- A toolkit for reproducible reinforcement learning research.☆1,919Updated last year
- A library of reinforcement learning components and agents☆3,585Updated last month
- Google DeepMind's software stack for physics-based simulation and Reinforcement Learning environments, using MuJoCo.☆3,924Updated this week
- A fork of OpenAI Baselines, implementations of reinforcement learning algorithms☆4,217Updated 2 years ago
- Reinforcement Learning Coach by Intel AI Lab enables easy experimentation with state of the art Reinforcement Learning algorithms☆2,337Updated 2 years ago
- TF-Agents: A reliable, scalable and easy to use TensorFlow library for Contextual Bandits and Reinforcement Learning.☆2,858Updated last week
- An API standard for multi-agent reinforcement learning environments, with popular reference environments and related utilities☆2,767Updated this week
- The Arcade Learning Environment (ALE) -- a platform for AI research.☆2,229Updated this week
- TensorFlow Reinforcement Learning☆3,139Updated 2 years ago
- A platform for Reasoning systems (Reinforcement Learning, Contextual Bandits, etc.)☆3,587Updated last month
- Rainbow is all you need! A step-by-step tutorial from DQN to Rainbow☆1,909Updated 3 months ago
- Reinforcement Learning in PyTorch☆2,239Updated 4 years ago
- Simple and easily configurable grid world environments for reinforcement learning☆2,174Updated last week
- Tensorforce: a TensorFlow library for applied reinforcement learning☆3,299Updated 6 months ago
- Learning Latent Dynamics for Planning from Pixels☆1,185Updated last year
- A simple OpenAI Gym environment for single and multi-agent reinforcement learning☆742Updated last year
- MuJoCo is a physics engine for detailed, efficient rigid body simulations with contacts. mujoco-py allows using MuJoCo from Python 3.☆2,921Updated last year
- Rainbow: Combining Improvements in Deep Reinforcement Learning☆1,602Updated 3 years ago
- Pytorch Implementation of DQN / DDQN / Prioritized replay/ noisy networks/ distributional values/ Rainbow/ hierarchical RL☆3,069Updated 3 years ago
- rllab is a framework for developing and evaluating reinforcement learning algorithms, fully compatible with OpenAI Gym.☆2,936Updated last year
- A collection of 100+ pre-trained RL agents using Stable Baselines, training and hyperparameter optimization included.☆1,153Updated 2 years ago
- High-quality single file implementation of Deep Reinforcement Learning algorithms with research-friendly features (PPO, DQN, C51, DDPG, T…☆6,327Updated 3 weeks ago
- A Platform for Many-Agent Reinforcement Learning☆1,711Updated 2 years ago
- A clean implementation based on AlphaZero for any game in any framework + tutorial + Othello/Gobang/TicTacToe/Connect4 and more☆4,034Updated last month
- SEED RL: Scalable and Efficient Deep-RL with Accelerated Central Inference. Implements IMPALA and R2D2 algorithms in TF2 with SEED's arch…☆800Updated 2 years ago
- Modularized Implementation of Deep RL Algorithms in PyTorch☆3,259Updated 10 months ago
- Procgen Benchmark: Procedurally-Generated Game-Like Gym-Environments☆1,048Updated last year
- MuZero☆2,577Updated 5 months ago
- An algorithm that generalizes the paradigm of self-play reinforcement learning and search to imperfect-information games.☆664Updated 10 months ago