Curriculum guide

Goal

Move from the mechanics of robot learning to the ability to design, implement, and evaluate a small modern system. The sequence is cumulative: later sessions reuse the same task contract, dataset format, and evaluation habits established in weeks 1–3.

What is on each lecture page

• Every page of the complete source lecture deck, rendered locally
• An original concept diagram designed for this study group
• A compact method/component comparison
• Key equations with implementation interpretation
• Common failure modes and diagnostics
• A measurable build milestone
• Primary paper and project references where useful

The locally rendered decks retain the copyright and reuse terms of the source material. The additional notes and diagrams are independent study-group material.

Tracks

• Core: read the guide, join the discussion, and complete the minimal build milestone.
• Builder: reproduce a result and submit code plus a short experiment report.
• Presenter: lead one paper discussion using claim → evidence → limitation → next experiment.

Recommended common task

Use one lightweight task for several weeks so algorithm differences remain interpretable. Good choices are a simulated reaching task, planar pushing, or a small grid-world for the earliest sessions. Define:

• observation and action spaces;
• success and safety metrics;
• reset and termination rules;
• demonstration and evaluation distributions;
• compute budget and random seeds.

Reading list by week

Week	Suggested discussion papers
1	No required paper; agree on task and evaluation conventions.
2	Simple random search provides a competitive approach to RL; Deep RL Doesn’t Work Yet; Curiosity-driven Exploration
3	Causal Confusion in Imitation Learning; Representation Learning for Visual Imitation; Transporter Networks
4	Evolution Strategies as a Scalable Alternative to RL; Learning Synergies Between Pushing and Grasping; Human-in-the-loop RL for Dexterous Manipulation
5	End-to-End Training of Deep Visuomotor Policies; Eureka; Latent Plans for Task-Agnostic Offline RL
6	Diffuser; Implicit Behavioral Cloning; Steering Your Diffusion Policy with Latent Space RL
7	Decision Transformer; ALOHA; Humanoid Locomotion as Next Token Prediction
8	Universal Policies via Text-Guided Video Generation; Training Agents Inside Scalable World Models; World Action Models are Zero-shot Policies
9	Language Conditioned Imitation Learning; Gato; π*0.6
10	In-Context Imitation Learning; Voyager; Training Strategies for Efficient Embodied Reasoning
11	A Path Towards Autonomous Machine Intelligence; The Bitter Lesson; Intelligence without Representation

The official course page is the source of truth for its schedule and links.

Capstone checkpoint

By week 11, each team should have a one-page proposal containing a falsifiable question, baseline, intervention, dataset/task, primary metric, compute estimate, ablations, and a stop condition. Prefer a small clean result over an unbounded platform build.