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

• URL: http://arxiv.org/abs/2603.02104v1
• Date: Mon, 02 Mar 2026 17:23:09 GMT
• Title: ACDC: Adaptive Curriculum Planning with Dynamic Contrastive Control for Goal-Conditioned Reinforcement Learning in Robotic Manipulation
• Abstract summary: ACDC integrates multidimensional Adaptive Curriculum (AC) Planning with Dynamic Contrastive (DC) Control to guide the agent along a well-designed learning trajectory.<n>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.
• Score: 7.4400459176733635
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• 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 papers

• Beyond Flat Policies: Hierarchical Post-Training for Embodied Agents in Robotic Manipulation [34.87301719899886]
  Vision-language-action (VLA) models have demonstrated remarkable capabilities in robotic manipulation by leveraging pretrained vision-language models.<n>Existing post-training methods predominantly optimize VLA models as flat policies, making it difficult to explicitly model task progression and perform robust long-horizon manipulation.<n>We propose Hierarchical Robotic Control (HiRoC), a hierarchical post-training framework that decouples high-level task planning from low-level action execution.
  arXiv  Detail & Related papers  (2026-08-06T13:07:56Z)
• EASy: Towards Efficient LLM-Based Agentic System [54.10819421625103]
  We propose EASy, a trainable agentic framework that jointly optimize task performance and computational efficiency through reinforcement learning.<n> EASy equips an LLM-based orchestrator with explicit knowledge of the capability and cost profiles of heterogeneous executors, enabling context-sensitive coordination beyond performance-only routing.<n>It further introduces a milestone-plan-act workflow that decomposes complex tasks into manageable milestones, constructs dependency-aware execution graphs, assigns suitable executors, and parallelizes independent steps while adapting subsequent decisions to intermediate outcomes.
  arXiv  Detail & Related papers  (2026-08-05T08:50:36Z)
• Language-Grounded Decoupled Action Representation for Robotic Manipulation [78.42228162226839]
  We propose the Language-Grounded Decoupled Action Representation (LaDA) framework to connect perception and control.<n>LaDA introduces a fine-grained intermediate layer of three interpretable action primitives--translation, rotation, and gripper control--providing explicit semantic structure for low-level actions.<n>It further employs a semantic-guided soft-label contrastive learning objective to align similar action primitives across tasks, enhancing generalization and motion consistency.
  arXiv  Detail & Related papers  (2026-03-13T13:08:26Z)
• On-the-Fly VLA Adaptation via Test-Time Reinforcement Learning [61.38273866396522]
  Vision-Language-Action models have emerged as a powerful paradigm for general-purpose robot learning.<n>Current methods remain unsuitable for challenging simulated- or physical-world deployments.<n>We introduce a Test-Time Reinforcement Learning for VLAs framework that enables on-the-fly policy adaptation during inference.
  arXiv  Detail & Related papers  (2026-01-11T01:51:30Z)
• TEACH: Temporal Variance-Driven Curriculum for Reinforcement Learning [8.366600075241847]
  We propose a novel Student-Teacher learning paradigm with a Temporal Variance-Driven Curriculum to accelerate Goal-Conditioned RL.<n>In this framework, the teacher module dynamically prioritizes goals with the highest temporal variance in the policy's confidence score.<n>We demonstrate this through evaluation across 11 diverse robotic manipulation and maze navigation tasks.
  arXiv  Detail & Related papers  (2025-12-28T07:29:29Z)
• CARL: Critical Action Focused Reinforcement Learning for Multi-Step Agent [53.56274149236814]
  We propose CARL, a critical-action-focused reinforcement learning algorithm tailored for multi-step agents.<n>Carl achieves both stronger performance and higher efficiency during training and inference across diverse evaluation settings.
  arXiv  Detail & Related papers  (2025-12-04T16:15:46Z)
• Application of LLM Guided Reinforcement Learning in Formation Control with Collision Avoidance [1.1718316049475228]
  Multi-Agent Systems (MAS) excel at accomplishing complex objectives through the collaborative efforts of individual agents.<n>In this paper, we introduce a novel framework that aims to overcome the challenge of designing an effective reward function.<n>By giving large language models (LLMs) on the prioritization of tasks, our framework generates reward functions that can be dynamically adjusted online.
  arXiv  Detail & Related papers  (2025-07-22T09:26:00Z)
• Learning from Reward-Free Offline Data: A Case for Planning with Latent Dynamics Models [79.2162092822111]
  We systematically evaluate reinforcement learning (RL) and control-based methods on a suite of navigation tasks.<n>We employ a latent dynamics model using the Joint Embedding Predictive Architecture (JEPA) and employ it for planning.<n>Our results show that model-free RL benefits most from large amounts of high-quality data, whereas model-based planning generalizes better to unseen layouts.
  arXiv  Detail & Related papers  (2025-02-20T18:39:41Z)
• CAIMAN: Causal Action Influence Detection for Sample-efficient Loco-manipulation [17.94272840532448]
  We present CAIMAN, a reinforcement learning framework that encourages robots to gain control over other entities in the environment.<n>We empirically demonstrate CAIMAN's superior sample efficiency and adaptability to diverse scenarios in simulation.
  arXiv  Detail & Related papers  (2025-02-02T16:16:53Z)
• Active Learning of Discrete-Time Dynamics for Uncertainty-Aware Model Predictive Control [46.81433026280051]
  We present a self-supervised learning approach that actively models the dynamics of nonlinear robotic systems. Our approach showcases high resilience and generalization capabilities by consistently adapting to unseen flight conditions.
  arXiv  Detail & Related papers  (2022-10-23T00:45:05Z)
• Effective Adaptation in Multi-Task Co-Training for Unified Autonomous Driving [103.745551954983]
  In this paper, we investigate the transfer performance of various types of self-supervised methods, including MoCo and SimCLR, on three downstream tasks. We find that their performances are sub-optimal or even lag far behind the single-task baseline. We propose a simple yet effective pretrain-adapt-finetune paradigm for general multi-task training.
  arXiv  Detail & Related papers  (2022-09-19T12:15:31Z)
• Deep Reinforcement Learning with Adaptive Hierarchical Reward for MultiMulti-Phase Multi Multi-Objective Dexterous Manipulation [11.638614321552616]
  Varying priority makes a robot hardly or even failed to learn an optimal policy with a deep reinforcement learning (DRL) method. We develop a novel Adaptive Hierarchical Reward Mechanism (AHRM) to guide the DRL agent to learn manipulation tasks with multiple prioritized objectives. The proposed method is validated in a multi-objective manipulation task with a JACO robot arm.
  arXiv  Detail & Related papers  (2022-05-26T15:44:31Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.