{ "name": "spinning-up-deep-rl", "description": "Knowledge base from \"Spinning Up in Deep RL\" by Joshua Achiam (OpenAI, MIT-licensed). Use when applying Achiam's frameworks for RL fundamentals and MDPs, the model-free algorithm taxonomy, policy gradient derivations, the six reference algorithms (VPG, TRPO, PPO, DDPG, TD3, SAC), debugging silently-failing RL code, or running rigorous multi-seed RL experiments.", "version": "1.0.0", "author": { "name": "Alireza Rezvani", "url": "https://github.com/alirezarezvani" }, "homepage": "https://github.com/alirezarezvani/claude-skills/tree/main/engineering/spinning-up-deep-rl", "repository": "https://github.com/alirezarezvani/claude-skills", "license": "MIT", "skills": [ "./skills/spinning-up-deep-rl" ] }