Mila Researcher Releases Open Robot Learning Textbook, First Draft Chapters Online
GlenBerseth · x · 2026-10-26
Glen Berseth, researcher at Université de Montréal / Mila, has released an open textbook Robot Learning built from three years of lecture notes, slides, and recordings of his graduate course. The first two draft chapters cover what robot learning is (and how to make control less brittle) and imitation learning from ALVINN to today's VLA models.
The full curriculum spans behavior cloning, planning and model-based RL, policy gradients, Q-learning, goal-conditioned and language-guided RL, LLM-designed reward functions, hierarchical and offline RL, and sim-to-real transfer — with videos, slides, Colabs, and programming assignments (in progress) on GitHub. More chapters are coming.
Related event: Mila Researcher Releases Open Robot Learning Textbook(2 posts)→
More from Embodied
- Tesla Cybercab convoy filmed driving in formation on highway — yunta_tsai · 2026-10-26
- Voicebuds: whisper to your computer quietly in an open office — tianshi_li · 2026-10-26
- Tesla Cybercab spotted in the wild as self-driving plus voice AI assistant rolls out — handotdev · 2026-10-26
- Tesla Robotaxis Spotted Busy Around Austin F1 Grand Prix — yunta_tsai · 2026-10-26
- Humanoid robot Tiangong Ultra runs 100m final in 8.64 seconds in Beijing — ingliguori · 2026-10-26
- Robots that read anticipatory brain signals for collaborative task planning — paper pick of the week — tomssilver · 2026-10-26