Behavior Cloning & Distribution Shift in Robot Manipulation
Interactive behavior-cloning manipulation policy: a k-nearest-neighbor regression policy learns from recorded expert demonstrations, and you control how far test rollouts start outside the training distribution to watch covariate shift and compounding error live.
Instead of hand-coding a control law, this simulator trains a manipulation policy the way real learning-based robots are trained: by cloning an expert's demonstrations. Recorded (state, action) pairs from an idealized expert form a training dataset, and a k-nearest-neighbor regression policy reproduces the expert's behavior anywhere near that data. Push the rollout's start point outside the demonstrated region and watch covariate shift take hold live — the policy's commanded direction gets noisier the farther it is from any demonstration, the gripper drifts into even less-covered territory, and the error compounds exactly as it does in real imitation-learning failures, the core problem that motivated on-policy corrections like DAgger and RL fine-tuning.
A k-nearest-neighbor behavior-cloning policy learns a manipulation task from recorded expert demonstrations; push test rollouts outside the training region to watch covariate shift and compounding error take hold live.
3D · Three.js / WebGL renderer · 60 FPS target · runs fully client-side, no install