Hybrid Action Based Reinforcement Learning for Multi-Objective Compatible Autonomous Driving

TL;DR

This paper introduces a novel multi-objective ensemble-critic reinforcement learning approach with hybrid actions, enhancing autonomous driving by balancing multiple objectives and improving policy learning and execution.

Contribution

It proposes a new architecture combining ensemble-critic and hybrid parameterized actions to better handle multi-objective autonomous driving scenarios.

Findings

Efficiently learns multi-objective policies in simulation and real datasets.

Improves action consistency, safety, and efficiency in highway driving scenarios.

Supports faster learning through an uncertainty-based exploration mechanism.

Abstract

Reinforcement Learning (RL) has shown excellent performance in solving decision-making and control problems of autonomous driving, which is increasingly applied in diverse driving scenarios. However, driving is a multi-attribute problem, leading to challenges in achieving multi-objective compatibility for current RL methods, especially in both policy updating and policy execution. On the one hand, a single value evaluation network limits the policy updating in complex scenarios with coupled driving objectives. On the other hand, the common single-type action space structure limits driving flexibility or results in large behavior fluctuations during policy execution. To this end, we propose a Multi-objective Ensemble-Critic reinforcement learning method with Hybrid Parametrized Action for multi-objective compatible autonomous driving. Specifically, an advanced MORL architecture is constructed, in which the ensemble-critic focuses on different objectives through independent reward functions. The architecture integrates a hybrid parameterized action space structure, and the generated driving actions contain both abstract guidance that matches the hybrid road modality and concrete control commands. Additionally, an uncertainty-based exploration mechanism that supports hybrid actions is developed to learn multi-objective compatible policies more quickly. Experimental results demonstrate that, in both simulator-based and HighD dataset-based multi-lane highway scenarios, our method efficiently learns multi-objective compatible autonomous driving with respect to efficiency, action consistency, and safety.