Mitigating Covariate Shift in Behavioral Cloning via Robust Stationary Distribution Correction
cs.LG, cs.AI
Submitted: 2026-11-06
Updated: 2026-11-06
Code: https://github.com/tzs930/drildice
Terminology
Sources
- D4RL: Datasets for Deep Data-Driven Reinforcement Learning
- Imitation Learning via Off-Policy Distribution Matching
- Distributionally Robust Optimization: A Review
- Statistical Properties of the log-cosh Loss Function Used in Machine Learning
- Feedback in Imitation Learning: The Three Regimes of Covariate Shift
Related papers
- A Physics-Regulated Neural Framework for Learning 3D Grain Growth Dynamics
- FlexMoE: Learning One-for-All Multi-Budget Expert Pruning for Flexible MoE Deployment
- OptiMind: Improving Small Language Models for Optimization Modeling through Formulation Guidance and Multi-Turn Learning
- Staying in the Sweet Spot: Boost Reasoning Evolution via Responsive Rollout Difficulty Manipulation
- Examining the Impact of Data and Training Methods on Emergent and Subliminal Misalignment
- Rethinking Black-Box On-Policy Distillation: A Rubric-based Analysis