Behavior-Constrained Reinforcement Learning with Receding-Horizon Credit Assignment for High-Performance Control

TL;DR

This paper introduces a behavior-constrained reinforcement learning method with receding-horizon prediction, enabling high-performance control policies that outperform baselines while closely adhering to expert human behavior in complex dynamic tasks.

Contribution

The authors propose a novel reinforcement learning framework that explicitly models and constrains deviation from expert behavior using trajectory-level look-ahead rewards and reference trajectories.

Findings

Policies achieve competitive lap times in high-fidelity race car simulation.

Learned policies closely match expert driving behavior and outperform baselines.

Human evaluation confirms policies reproduce expert-like driving characteristics.

Abstract

Learning high-performance control policies that remain consistent with expert behavior is a fundamental challenge in robotics. Reinforcement learning can discover high-performing strategies but often departs from desirable human behavior, whereas imitation learning is limited by demonstration quality and struggles to improve beyond expert data. We propose a behavior-constrained reinforcement learning framework that improves beyond demonstrations while explicitly controlling deviation from expert behavior. Because expert-consistent behavior in dynamic control is inherently trajectory-level, we introduce a receding-horizon predictive mechanism that models short-term future trajectories and provides look-ahead rewards during training. To account for the natural variability of human behavior under disturbances and changing conditions, we further condition the policy on reference trajectories, allowing it to represent a distribution of expert-consistent behaviors rather than a single deterministic target. Empirically, we evaluate the approach in high-fidelity race car simulation using data from professional drivers, a domain characterized by extreme dynamics and narrow performance margins. The learned policies achieve competitive lap times while maintaining close alignment with expert driving behavior, outperforming baseline methods in both performance and imitation quality. Beyond standard benchmarks, we conduct human-grounded evaluation in a driver-in-the-loop simulator and show that the learned policies reproduce setup-dependent driving characteristics consistent with the feedback of top-class professional race drivers. These results demonstrate that our method enables learning high-performance control policies that are both optimal and behavior-consistent, and can serve as reliable surrogates for human decision-making in complex control systems.