Reinforcement Learning for LLM ★ 5.000

An engineering course on reinforcement learning for LLMs and agentic systems: from MDPs, bandits, REINFORCE/PPO, and offline RL to reward models, RLHF/DPO, RLVR/GRPO, test-time search, agentic RL, infrastructure, and evaluation. In addition to the open lectures, the Stepik course includes more than 500 tasks: auto-graded tests, exercises with solutions, self-check questions with answers, and notebooks. The course is part of an evolving series on ML and LLMs.