Metta-AI / mettaLinks
A reinforcement learning codebase focusing on the emergence of cooperation and alignment in multi-agent AI systems.
☆124Updated last 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.☆197Updated last year
- A 3D video game environment and benchmark designed from scratch for reinforcement learning research☆188Updated 2 years ago
- An Open-Ended Agentic Simulator☆52Updated last year
- Exploitability calculation for imperfect-information game benchmarks☆31Updated 6 months ago
- ☆86Updated last month
- Reinforcement learning on general 2D physics environments in JAX. ICLR 2025 Oral.☆215Updated 3 weeks ago
- (Crafter + NetHack) in JAX. ICML 2024 Spotlight.☆346Updated 3 months ago
- Simple single-file baselines for Q-Learning in pure-GPU setting☆188Updated 7 months ago
- OMNI-EPIC: Open-endedness via Models of human Notions of Interestingness with Environments Programmed in Code (ICLR 2025).☆69Updated 10 months ago
- Cost aware hyperparameter tuning algorithm☆172Updated last year
- ☆22Updated last year
- ☆51Updated 3 months ago
- Efficient World Models with Context-Aware Tokenization. ICML 2024☆113Updated last year
- Skill Design From AI Feedback☆31Updated 8 months ago
- A toolkit for practical Human-AI cooperation research☆14Updated last year
- Simplest and Cleanest DreamerV3 implementation out there☆104Updated 7 months ago
- Accelerated minigrid environments with JAX☆151Updated 2 weeks ago
- The NetHack Learning Environment☆94Updated 2 months ago
- Synchronized Curriculum Learning for RL Agents☆114Updated 2 months ago
- Latent Program Network (from the "Searching Latent Program Spaces" paper)☆102Updated last month
- Highly scalable 2D JAX physics engine.☆60Updated 7 months ago
- Automated Capability Discovery via Foundation Model Self-Exploration☆65Updated 8 months ago
- Intrinsic Motivation from Artificial Intelligence Feedback☆131Updated last year
- Awesome Open-ended AI☆359Updated 2 weeks ago
- A framework for creating rich, 3D, Minecraft-like single and multi-agent environments for AI research. (Accepted at ICML 2025).☆137Updated 2 months ago
- OMNI: Open-endedness via Models of human Notions of Interestingness☆57Updated 9 months ago
- CleanRL's implementation of DeepMind's Podracer Sebulba Architecture for Distributed DRL☆116Updated last year
- fast + parallel AlphaZero in JAX☆104Updated 10 months ago
- ☆74Updated last year
- Learn online intrinsic rewards from LLM feedback☆44Updated 10 months ago