Metta-AI / metta
A reinforcement learning codebase focusing on the emergence of cooperation and alignment in multi-agent AI systems.
☆20Updated this week
Alternatives and similar repositories for metta:
Users that are interested in metta are comparing it to the libraries listed below
- An Open-Ended Agentic Simulator☆45Updated 7 months ago
- A framework for creating rich, 3D, Minecraft-like single and multi-agent environments for AI research based on Minetest☆66Updated this week
- A categorised list of Multi-Agent Reinforcemnt Learning (MARL) papers☆51Updated 2 years ago
- ☆21Updated 6 months ago
- Simple single-file baselines for Q-Learning in pure-GPU setting☆150Updated last week
- Efficient baselines for autocurricula in JAX.☆186Updated 7 months ago
- ☆74Updated last week
- Challenging Memory-based Deep Reinforcement Learning Agents☆95Updated 5 months ago
- Simulation Streams is a programming paradigm designed to efficiently control and leverage Large Language Models (LLMs) for complex, dynam…☆17Updated 2 weeks ago
- SocialJax: sequential social dilemma environments☆16Updated this week
- ☆14Updated last year
- A tool for aggregating and plotting MARL experiment data.☆76Updated 2 months ago
- Exploitability calculation for imperfect-information game benchmarks☆23Updated last month
- A collection of matrix games in JAX☆10Updated 4 months ago
- Benchmarks for Multi-Objective Multi-Agent Decision Making☆85Updated 2 weeks ago
- ☆70Updated last year
- Highly scalable 2D JAX physics engine.☆53Updated 2 weeks ago
- Official Implementation of "Can Learned Optimization Make Reinforcement Learning Less Difficult"☆22Updated 4 months ago
- Partially Observable Process Gym☆183Updated 8 months ago
- Benchmarking RL for POMDPs in Pure JAX [Code for "Structured State Space Models for In-Context Reinforcement Learning" (NeurIPS 2023)]☆99Updated last year
- Datasets with baselines for offline multi-agent reinforcement learning.☆162Updated this week
- Evaluating long-term memory of reinforcement learning algorithms☆141Updated last year
- 🪐 The Sebulba architecture to scale reinforcement learning on Cloud TPUs in JAX☆57Updated last year
- Accelerated minigrid environments with JAX☆132Updated 7 months ago
- A toolkit for practical Human-AI cooperation research☆14Updated 11 months ago
- a simple and scalable agent for training adaptive policies with sequence-based RL☆117Updated last month
- ⚡ Flashbax: Accelerated Replay Buffers in JAX☆228Updated last week
- Code for Discovered Policy Optimisation (NeurIPS 2022)☆9Updated last year
- (Crafter + NetHack) in JAX. ICML 2024 Spotlight.☆295Updated last month
- POPGym Library in JAX☆11Updated 11 months ago