Metta-AI / mettaLinks
A reinforcement learning codebase focusing on the emergence of cooperation and alignment in multi-agent AI systems.
☆116Updated this week
Alternatives and similar repositories for metta
Users that are interested in metta are comparing it to the libraries listed below
Sorting:
- Efficient baselines for autocurricula in JAX.☆196Updated last year
- A 3D video game environment and benchmark designed from scratch for reinforcement learning research☆188Updated 2 years ago
- (Crafter + NetHack) in JAX. ICML 2024 Spotlight.☆336Updated 3 months ago
- ☆22Updated last year
- An Open-Ended Agentic Simulator☆52Updated last year
- OMNI-EPIC: Open-endedness via Models of human Notions of Interestingness with Environments Programmed in Code (ICLR 2025).☆68Updated 9 months ago
- Reinforcement learning on general 2D physics environments in JAX. ICLR 2025 Oral.☆214Updated last week
- ☆48Updated 3 months ago
- ☆84Updated last month
- Simple single-file baselines for Q-Learning in pure-GPU setting☆186Updated 6 months ago
- Cost aware hyperparameter tuning algorithm☆171Updated last year
- Accelerated minigrid environments with JAX☆150Updated last month
- Awesome Open-ended AI☆343Updated 2 months ago
- 🏛️A research-friendly codebase for fast experimentation of single-agent reinforcement learning in JAX • End-to-End JAX RL☆359Updated this week
- A framework for creating rich, 3D, Minecraft-like single and multi-agent environments for AI research. (Accepted at ICML 2025).☆133Updated 2 months ago
- Simplest and Cleanest DreamerV3 implementation out there☆94Updated 6 months ago
- MiniHack the Planet: A Sandbox for Open-Ended Reinforcement Learning Research☆34Updated 2 months ago
- Hardware-Accelerated Reinforcement Learning Algorithms in pure Jax!☆236Updated 4 months ago
- Synchronized Curriculum Learning for RL Agents☆113Updated last month
- fast + parallel AlphaZero in JAX☆102Updated 9 months ago
- ⚡ Flashbax: Accelerated Replay Buffers in JAX☆253Updated 2 weeks ago
- Latent Program Network (from the "Searching Latent Program Spaces" paper)☆98Updated last week
- JAX-accelerated Meta-Reinforcement Learning Environments Inspired by XLand and MiniGrid 🏎️☆306Updated last month
- The NetHack Learning Environment☆92Updated last month
- Code for the paper "Harnessing Discrete Representations for Continual Reinforcement Learning"☆15Updated last year
- A toolkit for practical Human-AI cooperation research☆14Updated last year
- Automated Capability Discovery via Foundation Model Self-Exploration☆64Updated 8 months ago
- Intrinsic Motivation from Artificial Intelligence Feedback☆132Updated last year
- MR.Q is a general-purpose model-free reinforcement learning algorithm.☆112Updated 3 months ago
- Gymnasium environment for Pokemon Red☆41Updated last year