paper-with-me

Papers

Distributional Soft Actor-Critic with Harmonic Gradient for Safe and Efficient Autonomous Driving in Multi-lane Scenarios

2025-05-18 · Feihong Zhang, Guojian Zhan, Bin Shuai, Tianyi Zhang, Jingliang Duan, Shengbo Eben Li

Reinforcement learning (RL), known for its self-evolution capability, offers a promising approach to training high-level autonomous driving systems. However, handling constraints remains a significant challenge for existing RL algorithms, particularly in real-world applications. In this paper, we propose a new safety-oriented training technique called harmonic policy iteration (HPI). At each RL iteration, it first calculates two policy gradients associated with efficient driving and safety constraints, respectively. Then, a harmonic gradient is derived for policy updating, minimizing conflicts between the two gradients and consequently enabling a more balanced and stable training process. Furthermore, we adopt the state-of-the-art DSAC algorithm as the backbone and integrate it with our HPI to develop a new safe RL algorithm, DSAC-H. Extensive simulations in multi-lane scenarios demonstrate that DSAC-H achieves efficient driving performance with near-zero safety constraint violations.

📄 PDF Abstract BibTeX arXiv:2505.13532

Code (0)

등록된 구현이 없습니다.

Tasks

Autonomous DrivingReinforcement Learning (RL)

Methods 이 논문이 사용한 방법론

ADOPT Please enter a description about the method here

Similar Papers 제목 키워드 기반

Distributional Soft Actor-Critic: Off-Policy Reinforcement Learning for Addressing Value Estimation Errors

2020-01-09 · Jingliang Duan, Yang Guan, Shengbo Eben Li, Yangang Ren 외

In reinforcement learning (RL), function approximation errors are known to easily lead to the Q-value overestimations, thus greatly reducing policy performance. This paper presents a distributional soft actor-critic (DSA…

continuous-controlContinuous ControlMuJoCoreinforcement-learning+2

On Generalization and Distributional Update for Mimicking Observations with Adequate Exploration

2025-01-22 · Yirui Zhou, Xiaowei Liu, Xiaofeng Zhang, Yangchun Zhang

This paper tackles the efficiency and stability issues in learning from observations (LfO). We commence by investigating how reward functions and policies generalize in LfO. Subsequently, the built-in reinforcement learn…

Reinforcement Learning (RL)

Safe Langevin Soft Actor Critic

2026-01-31 · Mahesh Keswani, Samyak Jain, Raunak P. Bhattacharyya arxiv

Balancing reward and safety in constrained reinforcement learning remains challenging due to poor generalization from sharp value minima and inadequate handling of heavy-tailed risk distribution. We introduce Safe Langev…

Reinforcement Learning

Langevin Soft Actor-Critic: Efficient Exploration through Uncertainty-Driven Critic Learning

2025-01-29 · Haque Ishfaq, Guangyuan Wang, Sami Nur Islam, Doina Precup

Existing actor-critic algorithms, which are popular for continuous control reinforcement learning (RL) tasks, suffer from poor sample efficiency due to lack of principled exploration mechanism within them. Motivated by t…

continuous-controlContinuous ControlEfficient ExplorationReinforcement Learning (RL)+1

Distributional Soft Actor-Critic with Three Refinements

2023-10-09 · Jingliang Duan, Wenxuan Wang, Liming Xiao, Jiaxin Gao 외

Reinforcement learning (RL) has shown remarkable success in solving complex decision-making and control tasks. However, many model-free RL algorithms experience performance degradation due to inaccurate value estimation,…

Decision MakingReinforcement Learning (RL)