Dashboard
Your progress
Everything here lives only in your browser — no account, ever. Completion counts only what you actually did: chapters you read, and predictions you committed. Read it as an honest ledger, not a score to game.
0 of 43 chapters read. Completion counts only what you actually did — a chapter you read, and predictions you committed.
Nothing completed yet — read a chapter, or commit a prediction in an exercise, and it shows up here. No account needed; this lives only in your browser.
Phase 0 · Foundations
0/6 · 0%Phase 1 · Imitation
0/9 · 0%- 1.1Behavior Cloning: The Dumbest Thing That Works
- 1.2Data Is the Policy
- 1.3ACT: Commit to the Chunk
- 1.4Generative Policies I: Diffusion
- 1.5Generative Policies II: Flow Matching
- 1.6Evaluation Is Hard
- 1.7Tokens Meet Torques: The Tiny VLA, Part I (the data)
- 1.8The Tiny VLA II: Train It
- 1.9Graduation Bridge I: LeRobot for Real
Phase 2 · Reinforcement
0/8 · 0%- 2.1PPO: The Policy That Acts and Sees the Consequences
- 2.2SAC and the Off-Policy Bargain
- 2.34096 Robots at Once: PPO on MJX
- 2.4Reward Design Is Programming
- 2.5Locomotion: The Quadruped Walks
- 2.6Sim-to-Real Intuition Lab I: Latency & Noise
- 2.7Sim-to-Real Intuition Lab II: Randomize to Generalize
- 2.8Concepts of ROS, Without ROS: a Pub-Sub Control Runtime
Phase 3 · Advanced
0/9 · 0%- 3.1World Models I: Learning the Simulator
- 3.2World Models II: Acting in Imagination
- 3.3Build a Physics Engine I: Unconstrained Dynamics
- 3.4Build a Physics Engine II: Joints & Constraints
- 3.5Build a Physics Engine III: Contact
- 3.6Full Circle: Run Your ch1.1 Policy in the Engine You Built
- 3.7Datasets at Scale
- 3.8Reading the Frontier
- 3.9Plan Through Your Engine: Sampling-Based MPC (CEM / MPPI)
Phase 4 · Capstone
0/3 · 0%Phase 5 · Practitioner
0/8 · 0%- 5.1Patches & Attention: A ViT From Scratch
- 5.2Why Aligned: Contrastive Vision-Language Pretraining
- 5.3Control From Pixels: Visuomotor Behavior Cloning
- 5.4The Production VLA Shape: Prefix, Suffix, and the Action Expert
- 5.5FAST: Turning Torques into Tokens (DCT -> Quantize -> BPE)
- 5.6LoRA From Scratch: Adapt a Frozen Policy
- 5.7Quantize a Policy by Hand: INT8 Is a Scale, Not a Rounding
- 5.8The Real Loop: Teleoperate, Record, Train, Deploy — on a Real Arm's Body (in sim)
Milestones
0/11 earnedEvery milestone below is earned from real signals only — chapters you read and predictions you committed. Nothing here is awarded for just showing up.
- Got startedRead your first chapter end to end.
- Skin in the gameCommit your first predict-then-run answer before revealing it.
- Full marksRead a chapter and answer every one of its predictions.
- Phase 0 · Foundations completeFinish every chapter in Phase 0 · Foundations.
- Phase 1 · Imitation completeFinish every chapter in Phase 1 · Imitation.
- Phase 2 · Reinforcement completeFinish every chapter in Phase 2 · Reinforcement.
- Phase 3 · Advanced completeFinish every chapter in Phase 3 · Advanced.
- Phase 4 · Capstone completeFinish every chapter in Phase 4 · Capstone.
- Phase 5 · Practitioner completeFinish every chapter in Phase 5 · Practitioner.
- Halfway thereReach 50% overall completion across the curriculum.
- zero2robotReach 100% — every chapter read, every prediction in.