Towards a Reward-Free Reinforcement Learning Framework for Vehicle Control

TL;DR

This paper introduces a reward-free reinforcement learning framework for vehicle control that learns optimal policies without manually designed rewards, improving efficiency and adaptability in driving tasks.

Contribution

The proposed RFRLF framework directly learns target states for vehicle control using a target state prediction network and a reward-free policy network, eliminating the need for manual reward design.

Findings

Demonstrates effectiveness in vehicle driving control

Improves learning efficiency in reward-free settings

Adapts well to environments without explicit rewards

Abstract

Reinforcement learning plays a crucial role in vehicle control by guiding agents to learn optimal control strategies through designing or learning appropriate reward signals. However, in vehicle control applications, rewards typically need to be manually designed while considering multiple implicit factors, which easily introduces human biases. Although imitation learning methods does not rely on explicit reward signals, they necessitate high-quality expert actions, which are often challenging to acquire. To address these issues, we propose a reward-free reinforcement learning framework (RFRLF). This framework directly learns the target states to optimize agent behavior through a target state prediction network (TSPN) and a reward-free state-guided policy network (RFSGPN), avoiding the dependence on manually designed reward signals. Specifically, the policy network is learned via minimizing the differences between the predicted state and the expert state. Experimental results demonstrate the effectiveness of the proposed RFRLF in controlling vehicle driving, showing its advantages in improving learning efficiency and adapting to reward-free environments.