imitation learning
Imitation learning is a type of machine learning where an agent learns to perform tasks by mimicking the behavior of an expert or a teacher. This often involves observing demonstrations and learning a policy that replicates the actions of the demonstrator.
- A Smooth Sea Never Made a Skilled SAILOR: Robust Imitation via Learning to Search
- Act to See, See to Act: Diffusion-Driven Perception-Action Interplay for Adaptive Policies
- DexFlyWheel: A Scalable and Self-improving Data Generation Framework for Dexterous Manipulation
- DriveDPO: Policy Learning via Safety DPO For End-to-End Autonomous Driving
- Dynamic Test-Time Compute Scaling in Control Policy: Difficulty-Aware Stochastic Interpolant Policy
- EgoBridge: Domain Adaptation for Generalizable Imitation from Egocentric Human Data
- Failure Prediction at Runtime for Generative Robot Policies
- Faithful Dynamic Imitation Learning from Human Intervention with Dynamic Regret Minimization
- Flow Matching-Based Autonomous Driving Planning with Advanced Interactive Behavior Modeling
- How to Train Your LLM Web Agent: A Statistical Diagnosis
- Imitation Beyond Expectation Using Pluralistic Stochastic Dominance
- Inner Speech as Behavior Guides: Steerable Imitation of Diverse Behaviors for Human-AI coordination
- Interactive and Hybrid Imitation Learning: Provably Beating Behavior Cloning
- Learning from Demonstrations via Capability-Aware Goal Sampling
- MyoChallenge 2024: A New Benchmark for Physiological Dexterity and Agility in Bionic Humans
- No Experts, No Problem: Avoidance Learning from Bad Demonstrations
- Normalizing Flows are Capable Models for Continuous Control
- On the Global Optimality of Policy Gradient Methods in General Utility Reinforcement Learning
- Prioritizing Perception-Guided Self-Supervision: A New Paradigm for Causal Modeling in End-to-End Autonomous Driving
- Provable Ordering and Continuity in Vision-Language Pretraining for Generalizable Embodied Agents
- Quantifying Generalisation in Imitation Learning
- RAD: Training an End-to-End Driving Policy via Large-Scale 3DGS-based Reinforcement Learning
- Raw2Drive: Reinforcement Learning with Aligned World Models for End-to-End Autonomous Driving (in CARLA v2)
- Reinforcement Learning with Action Chunking
- Retrospective In-Context Learning for Temporal Credit Assignment with Large Language Models
- Self-Improving Embodied Foundation Models
- SonoGym: High Performance Simulation for Challenging Surgical Tasks with Robotic Ultrasound
- Structured Reinforcement Learning for Combinatorial Decision-Making
- SutureBot: A Precision Framework & Benchmark For Autonomous End-to-End Suturing
- Teaching Transformers to Solve Combinatorial Problems through Efficient Trial & Error
- Trajectory Graph Learning: Aligning with Long Trajectories in Reinforcement Learning Without Reward Design
- Videos are Sample-Efficient Supervisions: Behavior Cloning from Videos via Latent Representations
- World-aware Planning Narratives Enhance Large Vision-Language Model Planner