ACDC: Adaptive Curriculum Planning with Dynamic Contrastive Control for Goal-Conditioned Reinforcement Learning in Robotic Manipulation

arXiv:2603.02104v2 Announce Type: replace Abstract: 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.

Related

• Goal2Skill: Long-Horizon Manipulation with Adaptive Planning and Reflection
• V-CAGE: Vision-Closed-Loop Agentic Generation Engine for Robotic Manipulation
• RTMC: Step-Level Credit Assignment via Rollout Trees
• LEO-RobotAgent: A General-purpose Robotic Agent for Language-driven Embodied Operator
• Learning to Assist: Physics-Grounded Human-Human Control via Multi-Agent Reinforcement Learning

Source: arXiv cs.RO | 2026-04-15