behavior cloning
Behavior cloning is a supervised learning technique in reinforcement learning where the model learns to mimic the actions of an expert or a predefined policy from observed behavior, facilitating efficient learning.
- Coarse-to-fine Q-Network with Action Sequence for Data-Efficient Reinforcement Learning
- Generalizable Domain Adaptation for Sim-and-Real Policy Co-Training
- Imitation Beyond Expectation Using Pluralistic Stochastic Dominance
- Incentivizing Reasoning for Advanced Instruction-Following of Large Language Models
- Interactive and Hybrid Imitation Learning: Provably Beating Behavior Cloning
- Latent Policy Barrier: Learning Robust Visuomotor Policies by Staying In-Distribution
- Multi-Agent Imitation by Learning and Sampling from Factorized Soft Q-Function
- Offline imitation learning in $Q^\pi$-realizable MDPs without expert realizability
- Preference Distillation via Value based Reinforcement Learning
- Value-Guided Decision Transformer: A Unified Reinforcement Learning Framework for Online and Offline Settings
- VideoCAD: A Dataset and Model for Learning Long‑Horizon 3D CAD UI Interactions from Video
- Videos are Sample-Efficient Supervisions: Behavior Cloning from Videos via Latent Representations