paper-with-me

Papers

Knowledge-Guided Manipulation Using Multi-Task Reinforcement Learning

2026-03-25 · Aditya Narendra, Mukhammadrizo Maribjonov, Dmitry Makarov, Dmitry Yudin, Aleksandr Panov arxiv

This paper introduces Knowledge Graph based Massively Multi-task Model-based Policy Optimization (KG-M3PO), a framework for multi-task robotic manipulation in partially observable settings that unifies Perception, Knowledge, and Policy. The method augments egocentric vision with an online 3D scene graph that grounds open-vocabulary detections into a metric, relational representation. A dynamic-relation mechanism updates spatial, containment, and affordance edges at every step, and a graph neural encoder is trained end-to-end through the RL objective so that relational features are shaped directly by control performance. Multiple observation modalities (visual, proprioceptive, linguistic, and graph-based) are encoded into a shared latent space, upon which the RL agent operates to drive the control loop. The policy conditions on lightweight graph queries alongside visual and proprioceptive inputs, yielding a compact, semantically informed state for decision making. Experiments on a suite of manipulation tasks with occlusions, distractors, and layout shifts demonstrate consistent gains over strong baselines: the knowledge-conditioned agent achieves higher success rates, improved sample efficiency, and stronger generalization to novel objects and unseen scene configurations. These results support the premise that structured, continuously maintained world knowledge is a powerful inductive bias for scalable, generalizable manipulation: when the knowledge module participates in the RL computation graph, relational representations align with control, enabling robust long-horizon behavior under partial observability.

📄 PDF Abstract BibTeX arXiv:2603.24083

Code (0)

등록된 구현이 없습니다.

Tasks

Reinforcement LearningDecision Making

Similar Papers 제목 키워드 기반

Toward Deployable Multi-Robot Collaboration via a Symbolically-Guided Decision Transformer

2025-08-19 · Rathnam Vidushika Rasanji, Jin Wei-Kocsis, Jiansong Zhang, Dongming Gan 외 arxiv

Reinforcement learning (RL) has demonstrated great potential in robotic operations. However, its data-intensive nature and reliance on the Markov Decision Process (MDP) assumption limit its practical deployment in real-w…

Reinforcement LearningRobot ManipulationDecision Making

Relay Hindsight Experience Replay: Self-Guided Continual Reinforcement Learning for Sequential Object Manipulation Tasks with Sparse Rewards

2022-08-01 · Yongle Luo, Yuxin Wang, Kun Dong, Qiang Zhang 외

Exploration with sparse rewards remains a challenging research problem in reinforcement learning (RL). Especially for sequential object manipulation tasks, the RL agent always receives negative rewards until completing a…

FetchPush-v1Reinforcement Learning (RL)Robot Manipulation

VLGOR: Visual-Language Knowledge Guided Offline Reinforcement Learning for Generalizable Agents

2026-03-24 · Pengsen Liu, Maosen Zeng, Nan Tang, Kaiyuan Li 외 arxiv

Combining Large Language Models (LLMs) with Reinforcement Learning (RL) enables agents to interpret language instructions more effectively for task execution. However, LLMs typically lack direct perception of the physica…

Reinforcement LearningOffline RL

Intrinsic Language-Guided Exploration for Complex Long-Horizon Robotic Manipulation Tasks

2023-09-28 · Eleftherios Triantafyllidis, Filippos Christianos, Zhibin Li

Current reinforcement learning algorithms struggle in sparse and complex environments, most notably in long-horizon manipulation tasks entailing a plethora of different sequences. In this work, we propose the Intrinsical…

Decision Makingreinforcement-learningReinforcement Learning

Contact-Guided Exploration for Non-Prehensile Locomanipulation with Multi-Critic RL

2026-08-28 · Simone Tolomei, Mayank Mittal, Franco Angelini, Manolo Garabini 외 arxiv

Non-prehensile manipulation offers versatile skills for moving and rearranging heavy or bulky objects, particularly when combined with a mobile manipulation platform. However, both model-based and model-free approaches s…

Reinforcement Learning