mlsanityData to 14 Oct 2026

Boosting Deep Reinforcement Learning with Semantic Knowledge for Robotic Manipulators

arXiv 2601.16866 ↗First posted 23 Jan 2026cs.RO cs.AIcited by 0

On the map: Deep reinforcement learning methods → RL for robot locomotion and manipulation

Abstract (arXiv)

Deep Reinforcement Learning (DRL) is a powerful framework for solving complex sequential decision-making problems, particularly in robotic control. However, its practical deployment is often hindered by the substantial amount of experience required for learning, which results in high computational and time costs. In this work, we propose a novel integration of DRL with semantic knowledge in the form of Knowledge Graph Embeddings (KGEs), aiming to enhance learning efficiency by providing contextual information to the agent. Our architecture combines KGEs with visual observations, enabling the agent to exploit environmental knowledge during training. Experimental validation with robotic manipulators in environments featuring both fixed and randomized target attributes demonstrates that our method achieves up to 60% reduction in learning time and improves task accuracy by approximately 15 percentage points, without increasing training time or computational complexity. These results highlight the potential of semantic knowledge to reduce sample complexity and improve the effectiveness of DRL in robotic applications.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Placed in RL for robot locomotion and manipulation, one of 15 directions in Deep reinforcement learning methods. Builds on 20 of its 36 references that are in the map. First posted on arXiv 23 Jan 2026.

Builds on

20 of 36 references.

References · 20

  1. 2016Asynchronous Methods for Deep Reinforcement Learningcited by 2,258
  2. 2020robosuite: A Modular Simulation Framework and Benchmark for Robot Learningcited by 511
  3. 2018An Introduction to Deep Reinforcement Learningcited by 206
  4. 2023Grounding Large Language Models in Interactive Environments with Online Reinforcement Learningcited by 195
  5. 2019A Review of Robot Learning for Manipulation: Challenges, Representations, and Algorithmscited by 142
  6. 2017Robotic Pick-and-Place of Novel Objects in Clutter with Multi-Affordance Grasping and Cross-Domain Image Matchingcited by 125
  7. 2020Graph Constrained Reinforcement Learning for Natural Language Action Spacescited by 80
  8. 2024Reinforcement Learning Enhanced LLMs: A Surveycited by 71
  9. 2019IKEA Furniture Assembly Environment for Long-Horizon Complex Manipulation Taskscited by 69
  10. 2021Equivariant Q Learning in Spatial Action Spacescited by 62
  11. 2023Collaborating with language models for embodied reasoningcited by 61
  12. 2016Reinforcement Learning through Asynchronous Advantage Actor-Critic on a GPUcited by 48
8 more
  1. 2024SemGrasp: Semantic Grasp Generation via Language Aligned Discretizationcited by 29
  2. 2020Playing Text-Based Games with Common Sensecited by 21
  3. 2022Reinforcement learning on graphs: A surveycited by 20
  4. 2024The RL/LLM Taxonomy Tree: Reviewing Synergies Between Reinforcement Learning and Large Language Modelscited by 15
  5. 2018Intrinsically motivated reinforcement learning for human-robot interaction in the real-worldcited by 12
  6. 2019Adversary A3C for Robust Reinforcement Learningcited by 6
  7. 2023Exploiting Contextual Structure to Generate Useful Auxiliary Taskscited by 6
  8. 2020Investigating Simple Object Representations in Model-Free Deep Reinforcement Learningcited by 5

Built on by

Not cited yet.

Similar, not cited

Close in wording, no citation either way

  1. 2026Knowledge-Guided Manipulation Using Multi-Task Reinforcement Learning
  2. 2024Deep Reinforcement Learning for Robotics: A Survey of Real-World Successes
  3. 2025GUIDES: Guidance Using Instructor-Distilled Embeddings for Pre-trained Robot Policy Enhancement
  4. 2025Knowledge-Driven Imitation Learning: Enabling Generalization Across Diverse Conditions
  5. 2025UniJEPA: Enhancing Robot Policy via Unified Continuous and Discrete Representation Learning
  6. 2026Toward Unified Robot Learning: Bridging Representation, Vision-Language-Action, and World Models
  7. 2025Towards Autonomous Reinforcement Learning for Real-World Robotic Manipulation with Large Language Models
  8. 2026VLGOR: Visual-Language Knowledge Guided Offline Reinforcement Learning for Generalizable Agents