Work

Multi-Perspective Self-Supervised Learning-Guided Goal-Conditioned Reinforcement Learning

Year: 2025

Type: conference-paper

Abstract: Goal-conditioned reinforcement learning (GCRL) enables agents to accomplish specific tasks and demonstrates broad application prospects across multiple domains. However, in complex environments, task diversity significantly impacts policy training efficiency. To address this challenge, this paper proposes a multi-perspective self-supervised learning-guided goal-conditioned RL method. The approach introduces a goal relabeling mechanism to construct expert demonstrations from both exploration and exploitation perspectives. By leveraging behavioral cloning to learn distinct expert policies, the method enhances the learning efficiency of goal-conditioned RL. Experimental results on robotic manipulation tasks validate that our method effectively improves task success rates and convergence speed, demonstrating its feasibility in enhancing goal-conditioned RL performance in complex environments.

Source: International Conference on Computer Information and Big Data Applications (CIBDA)

DOI: 10.1145/3746709.3746751

Authors: Tao Wang, Zhi Li

Institution: Sichuan University

Language: English

Topic: Reinforcement Learning in Robotics

Subfield: Artificial Intelligence

Field: Computer Science

Domain: Physical Sciences

Open Access status: hybrid

OpenAlex ID: W4413845240

FWCI:

Cites: 8

Cited by:

Related to: 10