Burkov's new RL book implements REINFORCE, PPO and DQN on one rocket-landing task
burkov · x · 2026-11-11
Andriy Burkov (author of The Hundred-Page Machine Learning Book) announces a new book on deep RL: readers implement REINFORCE from scratch in PyTorch, then advance to PPO and Deep Q-Networks — all on the same rocket-landing task so each algorithm's learning behavior can be compared directly.
It also covers RLHF and verifiable rewards for language models. Buyers can request a coupon for $150 in free Lambda GPU credits; the book's small networks run on CPU, but GPUs are needed for real-world robot simulations or LLM finetuning.
Related event: Hundred-Page ML Book Author Releases Deep RL Book(2 posts)→
More from coding & agent
- Memgraph open-sources Context Graph: shared cross-session memory for Claude Code and Codex — JeremyCMorgan · 2026-11-11
- Fable 5.2-generated PR touches 3,000+ files, adds 441,926 lines in one change — cramforce · 2026-11-11
- Birthday gift: an AI agent emergently deployed the exact observability stack I wanted — sloppenheimer · 2026-11-11
- No Claude account? This DSH plugin lets you try Claude-style Whiteboards anyway — dotey · 2026-11-11
- Running 6 concurrent ds41-flash agents: persistent enough to need pi-durable coordination — dbreunig · 2026-11-11
- OpenAI roundup: architecture details of four GPT-Live voice agent builds — pbbakkum · 2026-11-11