in-context-reinforcement-learning

Agent S: an open agentic framework that uses computers like a human

🧠🔗 From idea to production in just few lines: Graph-Based Programmable Neuro-Symbolic LM Framework - a production-first LM framework built with decade old Deep Learning best practices

Awesome In-Context RL: A curated list of In-Context Reinforcement Learning - - —

Official Implementation for "In-Context Reinforcement Learning for Variable Action Spaces"

XLand-100B: A Large-Scale Multi-Task Dataset for In-Context Reinforcement Learning - - — ICLR 2025

Vintix: Action Model via In-Context Reinforcement Learning - - — ICML 2025

Official Implementation for "In-Context Reinforcement Learning from Noise Distillation"

Next-gen Foundation Model for Embodied AI

Xenoverse is a collection of randomized RL, Language, and general-purpose simulation environments, designed for training General-Purpose Learning Agents (GLAs).

Toy meta-RL environments for testing algorithms implementations

Grouped-Tied Attention by Zadouri, Strauss, Dao (2025).

Source code for reproducing free random projection

Explore the "frp_rl" repository to discover the Free Random Projection technique for in-context reinforcement learning. This project offers a JAX-based implementation that helps agents adapt and learn in diverse environments. 🐙🌟

Repository Switched To Xenoverse (https://github.com/FutureAGI/Xenoverse)

This repository, "frp_rl," implements Free Random Projection for in-context reinforcement learning, allowing agents to adapt seamlessly to new tasks. Explore the core components and algorithms to enhance your meta-learning experience! 🐙🌟

This repository offers a clear implementation of Free Random Projection for in-context reinforcement learning, focusing on effective adaptation and robust representation. Explore the core algorithms in the `frp_popjaxrl/` directory and enhance your understanding of meta-learning across diverse environments. 🐙✨