mlsanityData to 14 Oct 2026

Setting up a Reinforcement Learning Task with a Real-World Robot

arXiv 1803.07067 ↗First posted 19 Mar 2018cs.LG cs.AI cs.ROcited by 33

Not on the map. Why?

Abstract (arXiv)

Reinforcement learning is a promising approach to developing hard-to-engineer adaptive solutions for complex and diverse robotic tasks. However, learning with real-world robots is often unreliable and difficult, which resulted in their low adoption in reinforcement learning research. This difficulty is worsened by the lack of guidelines for setting up learning tasks with robots. In this work, we develop a learning task with a UR5 robotic arm to bring to light some key elements of a task setup and study their contributions to the challenges with robots. We find that learning performance can be highly sensitive to the setup, and thus oversights and omissions in setup details can make effective learning, reproducibility, and fair comparison hard. Our study suggests some mitigating steps to help future experimenters avoid difficulties and pitfalls. We show that highly reliable and repeatable experiments can be performed in our setup, indicating the possibility of reinforcement learning research extensively based on real-world robots.

Key facts. Cited by 33 papers in the map (data through 14 Oct 2026). First posted on arXiv 19 Mar 2018.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2021: 1; 2022: 8; 2023: 4; 2024: 9; 2025: 4; 2026: 7.

33 papers.

Sort:

By area:

  1. 2022Near-Optimal Regret for Adversarial MDP with Delayed Bandit Feedbackcited by 22
  2. 2022Asynchronous Reinforcement Learning for Real-Time Control of Physical Robotscited by 22
  3. 2022Delayed Reinforcement Learning by Imitationcited by 16
  4. 2022Real-Time Reinforcement Learning for Vision-Based Robotics Utilizing Local and Remote Computerscited by 13
  5. 2022Dynamic Decision Frequency with Continuous Optionscited by 13
  6. 2025Robustness and Cybersecurity in the EU Artificial Intelligence Actcited by 11
  7. 2024Boosting Reinforcement Learning with Strongly Delayed Feedback Through Auxiliary Short Delayscited by 10
  8. 2024Variational Delayed Policy Optimizationcited by 9
  9. 2024Reinforcement Learning for Blind Stair Climbing with Legged and Wheeled-Legged Robotscited by 8
  10. 2023A Reduction-based Framework for Sequential Decision Making with Delayed Feedbackcited by 7
  11. 2023DiAReL: Reinforcement Learning with Disturbance Awareness for Robust Sim2Real Policy Transfer in Robot Controlcited by 7
  12. 2023Delay-Adapted Policy Optimization and Improved Regret for Adversarial MDP with Delayed Bandit Feedbackcited by 6
21 more
  1. 2022RMBench: Benchmarking Deep Reinforcement Learning for Robotic Manipulator Controlcited by 5
  2. 2024Deployable Reinforcement Learning with Variable Control Ratecited by 5
  3. 2024Revisiting Scalable Hessian Diagonal Approximations for Applications in Reinforcement Learningcited by 5
  4. 2022A Prescriptive Dirichlet Power Allocation Policy with Deep Reinforcement Learningcited by 4
  5. 2025Model-Based Reinforcement Learning under Random Observation Delayscited by 3
  6. 2021What Robot do I Need? Fast Co-Adaptation of Morphology and Control using Graph Neural Networkscited by 2
  7. 2024Tree Search-Based Policy Optimization under Stochastic Execution Delaycited by 2
  8. 2024An Idiosyncrasy of Time-discretization in Reinforcement Learningcited by 2
  9. 2026Performance Variation in Deep Reinforcement Learningcited by 2
  10. 2022A Concise Introduction to Reinforcement Learning in Roboticscited by 1
  11. 2024Control in Stochastic Environment with Delays: A Model-based Reinforcement Learning Approachcited by 1
  12. 2025Belief-Based Offline Reinforcement Learning for Delay-Robust Policy Optimizationcited by 1
  13. 2025Reinforcement Learning via Conservative Agent for Environments with Random Delayscited by 1
  14. 2026Benchmarking Action Spaces in Reinforcement Learning for Vision-based Robotic Manipulationcited by 1
  15. 2026Physical Atari: A Robust and Accessible Platform for Real-time Reinforcement Learning on Robotscited by 1
  16. 2023Learning Visual Tracking and Reaching with Deep Reinforcement Learning on a UR10e Robotic Armcited by 0
  17. 2024Inverse Delayed Reinforcement Learningcited by 0
  18. 2026Delayed homomorphic reinforcement learning for environments with delayed feedbackcited by 0
  19. 2026Structural Equivalence and Learning Dynamics in Delayed MARLcited by 0
  20. 2026LangLoc: "Tell Me What You See"cited by 0
  21. 2026The Open Ant: A Robot Platform for Reinforcement Learning Researchcited by 0