Naman Vats's picture

Building on HF

Naman Vats PRO

namanvats

·

AI & ML interests

Make Open Source AI win

Recent Activity

liked a model about 11 hours ago

deepseek-ai/DeepSeek-V4-Flash

upvoted a collection 25 days ago

reacted to anakin87's post with ❤️ 26 days ago

How LLM training with RL Environments works? It all starts with 𝗥𝗲𝗶𝗻𝗳𝗼𝗿𝗰𝗲𝗺𝗲𝗻𝘁 𝗟𝗲𝗮𝗿𝗻𝗶𝗻𝗴 𝘄𝗶𝘁𝗵 𝗩𝗲𝗿𝗶𝗳𝗶𝗮𝗯𝗹𝗲 𝗥𝗲𝘄𝗮𝗿𝗱𝘀 - question asked - model generates reasoning + answer - answer checked against ground truth - reward drives RL training In this setup, the environment is simple: fixed questions and answers, rollout logic, reward(s) Consider a more complex tic-tac-toe env ❌⭕ It adds: - dynamic game generation/handling - tunable opponent skill - multi-turn interactions (envs can also include tools) --- What happens at training? We use 𝗚𝗿𝗼𝘂𝗽 𝗥𝗲𝗹𝗮𝘁𝗶𝘃𝗲 𝗣𝗼𝗹𝗶𝗰𝘆 𝗢𝗽𝘁𝗶𝗺𝗶𝘇𝗮𝘁𝗶𝗼𝗻 with a tic-tac-toe env No critic model needed, the group is the baseline Simpler than PPO 1️⃣ Rollout generation: from the same board, model plays N games via sampling 2️⃣ Each game scored with deterministic rewards (win, format, ...) 3️⃣ Mean score computed across the group 4️⃣ Each rollout's advantage = its score minus the group mean 5️⃣ Model updated to favor trajectories above baseline 🔁 Repeat For a deep dive, check out 🌱 https://github.com/anakin87/llm-rl-environments-lil-course a free hands-on course on RL environments for LLMs

View all activity

Organizations

namanvats 's datasets 1

namanvats/harbor-goose-openhands-benchmark

Viewer • Updated Apr 12 • 246 • 103 • 3