Lists (6)
Starred repositories
Emerge-Lab / nocturne_lab
Forked from facebookresearch/nocturneA data-driven, fast driving simulator for multi-agent coordination under partial observability.
Benchmarking Goal-Oriented Software Engineering
Codebase for the rational policy gradient algorithm and paper.
RewardBench: the first evaluation tool for reward models.
[NeurIPS 2025 & ICLR 2025 Financial AI Best Paper Award] A multi-agent framework that leverages LLMs to simulate socio-economic systems
Language modeling that treats text as images, leveraging visual structure for enhanced understanding.
LeanRL is a fork of CleanRL, where selected PyTorch scripts optimized for performance using compile and cudagraphs.
High throughput synchronous and asynchronous reinforcement learning
The official ElevenLabs MCP server
FlexAttention based, minimal vllm-style inference engine for fast Gemma 2 inference.
🏛️A research-friendly codebase for fast experimentation of single-agent reinforcement learning in JAX • End-to-End JAX RL
Open source interpretability artefacts for R1.
FULL Augment Code, Claude Code, Cluely, CodeBuddy, Comet, Cursor, Devin AI, Junie, Kiro, Leap.new, Lovable, Manus, NotionAI, Orchids.app, Perplexity, Poke, Qoder, Replit, Same.dev, Trae, Traycer AI…
Atropos is a Language Model Reinforcement Learning Environments framework for collecting and evaluating LLM trajectories through diverse environments
A reinforcement learning codebase focusing on the emergence of cooperation and alignment in multi-agent AI systems.
A compilation of the best multi-agent papers
Automating the Search for Artificial Life with Foundation Models!
Textbook on reinforcement learning from human feedback
Understanding the interplay between memorization and generalization in neural networks, featuring MAT, a learning algorithm to enhance robustness by mitigating spurious correlations.
Get up and running with OpenAI gpt-oss, DeepSeek-R1, Gemma 3 and other models.
Really Fast End-to-End Jax RL Implementations
LLM-Merging: Building LLMs Efficiently through Merging
BenchMARL is a library for benchmarking Multi-Agent Reinforcement Learning (MARL). BenchMARL allows to quickly compare different MARL algorithms, tasks, and models while being systematically ground…
A library for generative social simulation
A course on aligning smol models.