OpenClaw-RL: Train any agent simply by talking
🦞 Just talk to your agent — it learns and EVOLVES 🧬.
Let Skills Evolve Collectively with Agentic Evolver
[CoRL 2023] This repository contains data generation and training code for Scaling Up & Distilling Down
Gradient descent, but the parameters are agents — a parallel, asynchronous framework for self-evolving agents (skills, prompts, harnesses). Diffs are the gradients; the aggregator is the optimizer.
Physical AI runtime for embodied agents — governed action, verified experience, physical memory, and skill evolution.
SRA-Bench and SR-Agents: a benchmark and toolkit for skill-retrieval-augmented LLM agents.
Agent Skill Induction: "Inducing Programmatic Skills for Agentic Tasks"
[ICLR 2023] Choreographer: a world-model-based agent that discovers and learns unsupervised skills in latent imagination, and it's able to efficiently coordinate and adapt the skills to solve downstream tasks.
[ICML 2023] Pre-train world model-based agents with different unsupervised strategies, fine-tune the agent's components selectively, and use planning (Dyna-MPC) during fine-tuning.
PyTorch implementation for "Discovery of Incremental Skills" (DISk) algorithm from ICLR 2022 paper "One After Another: Learning Incremental Skills for a Changing World"
Official implementation of SPECI: Skill Prompts based Hierarchical Continual Imitation Learning for Robot Manipulation [IEEE TCDS]
Flow-driven recursive skill evolution for agentic LLM orchestration.
SkillNet-Gym: A Dynamic Benchmark for Compositional Skill Learning
GenPark AI Agent Skill - Autonomous skill code synthesizer, AST validator, sandboxed unit-test generator, and skill library archiver.
GenPark AI Agent Skill - Autonomous skill code synthesizer, AST validator, sandboxed unit-test generator, and skill library archiver.
A self-extending AI agent built with Google ADK & Gemini 2.0 Flash that dynamically creates, stores, and reuses its own skills at runtime — growing smarter with every task.
Trails 2nd Chapter Combat & Progression Utility for PC featuring damage/healing multipliers, damage reduction, EXP progression, one-hit stun, Brave value support, skill-learning controls, Reward/BP mission helpers, reusable presets, configs, and a clean trainer dashboard.
Follow along with my AI Agents Masterclass videos! All of the code I create and use in this series on YouTube will be here for you to use and even build on top of!
Collection of awesome LLM apps with AI Agents and RAG using OpenAI, Anthropic, Gemini and opensource models.
To associate your repository with the skill-learning topic, visit your repo's landing page and select "manage topics."