IMITATION-LEARNINGCURRENT2026-05-06

CRAFT: Counterfactual-to-Interactive Reinforcement Fine-Tuning for Driving Policies

Keyu Chen, Nanfei Ye, Yida Wang, Wenchao Sun, Danqi Zhao, Hao Cheng, Sifa Zheng

This solves a critical problem in autonomous driving: imitation-learned policies fail when they deviate from Robot LearningTrainingThe process of fitting a model using data or experience. data because they haven't learned to recover from mistakes. CRAFT lets you fine-tune driving policies with 10-30% performance gains on real closed-loop metrics by balancing cheap counterfactual predictions with expensive real driving interactions.

THE PROBLEM

This paper focuses on Imitation & Reinforcement LearningImitation Learning (IL)Teaching a robot by showing it examples of how to do a task.. This solves a critical problem in autonomous driving: imitation-learned policies fail when they deviate from Robot LearningTrainingThe process of fitting a model using data or experience. data because they haven't learned to recover from mistakes. CRAFT lets you fine-tune driving policies with 10-30% performance gains on real closed-loop metrics by balancing cheap counterfactual predictions with expensive real driving interactions. Read the paper by tracking the Core ConceptsTaskThe job the robot is supposed to complete, such as pick-and-place, navigation, or drawer opening. definition, the Core ConceptsRobotA physical system with sensors and actuators that can observe the world and take actions. or data assumptions, and the evidence that supports the claimed improvement.

HOW IT WORKS

1

Task framing

The paper frames the work as Imitation & Reinforcement LearningImitation Learning (IL)Teaching a robot by showing it examples of how to do a task.. Start here because it defines what success means and which assumptions the rest of the method inherits.

2

Core method

This solves a critical problem in autonomous driving: imitation-learned policies fail when they deviate from Robot LearningTrainingThe process of fitting a model using data or experience. data because they haven't learned to recover from mistakes. CRAFT lets you fine-tune driving policies with 10-30% performance gains on real closed-loop metrics by balancing cheap counterfactual predictions with expensive real driving interactions. When reading the method section, identify the inputs, the learned or engineered representation, and the Core ConceptsActionA command the robot sends to its motors, controller, or low-level system. or prediction produced by the system.

3

Data and supervision

For robotics work, the data story is part of the method: check whether the system depends on Imitation & Reinforcement LearningTeleoperation (teleop)A human remotely controlling the robot, often to collect demonstrations., Simulation & Sim-to-RealSimulationA virtual environment where robots can be trained or tested., internet video, human labels, or Core ConceptsRobotA physical system with sensors and actuators that can observe the world and take actions. rollouts.

4

Evaluation evidence

The paper should be judged through its Simulation & Sim-to-RealEvaluationMeasuring how well a robot system performs. protocol: what data is used, what Core ConceptsRobotA physical system with sensors and actuators that can observe the world and take actions. or simulator is tested, and which Evaluation & ResearchBaselineA reference method used for comparison. comparisons support the claim. Look for the gap between the headline result and the Simulation & Sim-to-RealDeploymentPutting the trained system on a real robot. setting you would actually care about.

FIGURES

KEY RESULTS

Main contributionConceptual contribution

This solves a critical problem in autonomous driving: imitation-learned policies fail when they deviate from Robot LearningTrainingThe process of fitting a model using data or experience. data because they haven't learned to recover from mistakes. CRAFT lets you fine-tune driving policies with 10-30% performance gains on real closed-loop metrics by balancing cheap counterfactual predictions with expensive real driving interactions.

WHY DEVELOPERS SHOULD CARE

This solves a critical problem in autonomous driving: imitation-learned policies fail when they deviate from Robot LearningTrainingThe process of fitting a model using data or experience. data because they haven't learned to recover from mistakes. CRAFT lets you fine-tune driving policies with 10-30% performance gains on real closed-loop metrics by balancing cheap counterfactual predictions with expensive real driving interactions.

LIMITATIONS

The main limitation to check is whether the claimed behavior holds outside the paper's reported setup. That means testing across different Core ConceptsRobotA physical system with sensors and actuators that can observe the world and take actions. embodiments, scenes, objects, and data distributions.

WHAT COMES NEXT

The practical next step is independent reproduction with clear baselines, ablations, and stress tests. For a developer, the useful follow-up is to map the paper's Imitation & Reinforcement LearningImitation Learning (IL)Teaching a robot by showing it examples of how to do a task. assumptions onto a concrete Core ConceptsRobotA physical system with sensors and actuators that can observe the world and take actions. stack, then test the smallest version of the method that could run end to end.

RELATED PAPERS