Enregistré dans:
Détails bibliographiques
Auteurs principaux: Wang, Xuerui, Ren, Guangyu, Dai, Tianhong, Hu, Bintao, Huang, Shuangyao, Zhang, Wenzhang, Liu, Hengyan
Format: Preprint
Publié: 2026
Sujets:
Accès en ligne:https://arxiv.org/abs/2603.02104
Tags: Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
_version_ 1866908960417644544
author Wang, Xuerui
Ren, Guangyu
Dai, Tianhong
Hu, Bintao
Huang, Shuangyao
Zhang, Wenzhang
Liu, Hengyan
author_facet Wang, Xuerui
Ren, Guangyu
Dai, Tianhong
Hu, Bintao
Huang, Shuangyao
Zhang, Wenzhang
Liu, Hengyan
contents Goal-conditioned reinforcement learning has shown considerable potential in robotic manipulation; however, existing approaches remain limited by their reliance on prioritizing collected experience, resulting in suboptimal performance across diverse tasks. Inspired by human learning behaviors, we propose a more comprehensive learning paradigm, ACDC, which integrates multidimensional Adaptive Curriculum (AC) Planning with Dynamic Contrastive (DC) Control to guide the agent along a well-designed learning trajectory. More specifically, at the planning level, the AC component schedules the learning curriculum by dynamically balancing diversity-driven exploration and quality-driven exploitation based on the agent's success rate and training progress. At the control level, the DC component implements the curriculum plan through norm-constrained contrastive learning, enabling magnitude-guided experience selection aligned with the current curriculum focus. Extensive experiments on challenging robotic manipulation tasks demonstrate that ACDC consistently outperforms the state-of-the-art baselines in both sample efficiency and final task success rate.
format Preprint
id arxiv_https___arxiv_org_abs_2603_02104
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle ACDC: Adaptive Curriculum Planning with Dynamic Contrastive Control for Goal-Conditioned Reinforcement Learning in Robotic Manipulation
Wang, Xuerui
Ren, Guangyu
Dai, Tianhong
Hu, Bintao
Huang, Shuangyao
Zhang, Wenzhang
Liu, Hengyan
Robotics
Goal-conditioned reinforcement learning has shown considerable potential in robotic manipulation; however, existing approaches remain limited by their reliance on prioritizing collected experience, resulting in suboptimal performance across diverse tasks. Inspired by human learning behaviors, we propose a more comprehensive learning paradigm, ACDC, which integrates multidimensional Adaptive Curriculum (AC) Planning with Dynamic Contrastive (DC) Control to guide the agent along a well-designed learning trajectory. More specifically, at the planning level, the AC component schedules the learning curriculum by dynamically balancing diversity-driven exploration and quality-driven exploitation based on the agent's success rate and training progress. At the control level, the DC component implements the curriculum plan through norm-constrained contrastive learning, enabling magnitude-guided experience selection aligned with the current curriculum focus. Extensive experiments on challenging robotic manipulation tasks demonstrate that ACDC consistently outperforms the state-of-the-art baselines in both sample efficiency and final task success rate.
title ACDC: Adaptive Curriculum Planning with Dynamic Contrastive Control for Goal-Conditioned Reinforcement Learning in Robotic Manipulation
topic Robotics
url https://arxiv.org/abs/2603.02104