google-deepmind / lab2d
A customisable 2D platform for agent-based AI research
☆422Updated last year
Related projects ⓘ
Alternatives and complementary repositories for lab2d
- Code for Go-Explore: a New Approach for Hard-Exploration Problems☆557Updated last year
- A Python interface for reinforcement learning environments☆344Updated last year
- Benchmarking the Spectrum of Agent Capabilities☆382Updated 9 months ago
- A grid-world game engine for game AI research☆233Updated 7 months ago
- Real-World RL Benchmark Suite☆346Updated 4 years ago
- The project is a platform of zero learning with a library of games.☆266Updated 3 years ago
- MiniHack the Planet: A Sandbox for Open-Ended Reinforcement Learning Research☆478Updated 2 months ago
- Tonic RL library☆404Updated 3 months ago
- DeepMind Alchemy task environment: a meta-reinforcement learning benchmark☆197Updated last year
- Paired Open-Ended Trailblazer (POET) and Enhanced POET☆242Updated 2 years ago
- A set of 13 diverse machine-learning tasks that require memory to solve.☆221Updated 3 years ago
- Dream to Control: Learning Behaviors by Latent Imagination☆607Updated 4 years ago
- A library that makes Evolutionary Strategies (ES) simple to use.☆179Updated 3 years ago
- High-throughput simulation platform for Artificial Intelligence reseach☆219Updated last year
- Research code implementing the search AI agent for Hanabi, as well as a web server so people can play against it☆127Updated last year
- Pytorch Implementation of MuZero☆343Updated last year
- A simple OpenAI Gym environment for single and multi-agent reinforcement learning☆727Updated 10 months ago
- Dream to Control: Learning Behaviors by Latent Imagination☆513Updated 3 years ago
- ☆313Updated last year
- DQN Zoo is a collection of reference implementations of reinforcement learning agents developed at DeepMind based on the Deep Q-Network (…☆455Updated 7 months ago
- megastep helps you build 1-million FPS reinforcement learning environments on a single GPU☆133Updated 2 years ago
- ☆1,258Updated last month
- Reverb is an efficient and easy-to-use data storage and transport system designed for machine learning research☆704Updated this week
- a Lightweight library for sequential learning agents, including reinforcement learning☆427Updated last year
- Procgen Benchmark: Procedurally-Generated Game-Like Gym-Environments☆1,018Updated 10 months ago
- High throughput synchronous and asynchronous reinforcement learning☆823Updated 2 weeks ago
- hanabi_learning_environment is a research platform for Hanabi experiments.☆645Updated last year
- Extremely Fast End-to-End Deep Multi-Agent Reinforcement Learning Framework on a GPU (JMLR 2022)☆464Updated 3 months ago
- RLMeta is a light-weight flexible framework for Distributed Reinforcement Learning Research.☆284Updated last year
- A PyTorch library for building deep reinforcement learning agents.☆646Updated 7 months ago