mlsanityData to 7 Oct 2026

Unsupervised Reward Shaping for a Robotic Sequential Picking Task from Visual Observations in a Logistics Scenario

arXiv 2209.12350 ↗First posted 25 Sep 2022cs.RO cs.LG cs.SYcited by 0

Not on the map. Why?

Abstract (arXiv)

We focus on an unloading problem, typical of the logistics sector, modeled as a sequential pick-and-place task. In this type of task, modern machine learning techniques have shown to work better than classic systems since they are more adaptable to stochasticity and better able to cope with large uncertainties. More specifically, supervised and imitation learning have achieved outstanding results in this regard, with the shortcoming of requiring some form of supervision which is not always obtainable for all settings. On the other hand, reinforcement learning (RL) requires much milder form of supervision but still remains impracticable due to its inefficiency. In this paper, we propose and theoretically motivate a novel Unsupervised Reward Shaping algorithm from expert's observations which relaxes the level of supervision required by the agent and works on improving RL performance in our task.

Key facts. No citing papers in the map yet (data through 7 Oct 2026). Builds on 21 of its 33 references that are in the map. First posted on arXiv 25 Sep 2022.

Builds on

21 of 33 references.

References · 21

  1. 2015Deep Residual Learning for Image Recognitioncited by 51,809
  2. 2020An Image is Worth 16x16 Words: Transformers for Image Recognition at Scalecited by 29,915
  3. 2022Generative Adversarial Networkscited by 5,603
  4. 2013Playing Atari with Deep Reinforcement Learningcited by 3,211
  5. 2015Deep Reinforcement Learning with Double Q-learningcited by 1,704
  6. 2016Generative Adversarial Imitation Learningcited by 1,576
  7. 2016Least Squares Generative Adversarial Networkscited by 1,000
  8. 2015End-to-End Training of Deep Visuomotor Policiescited by 847
  9. 2018QT-Opt: Scalable Deep Reinforcement Learning for Vision-Based Robotic Manipulationcited by 730
  10. 2018Which Training Methods for GANs do actually Converge?cited by 672
  11. 2018An Algorithmic Perspective on Imitation Learningcited by 455
  12. 2020Transporter Networks: Rearranging the Visual World for Robotic Manipulationcited by 342
9 more
  1. 2019A Divergence Minimization Perspective on Imitation Learning Methodscited by 188
  2. 2019kPAM: KeyPoint Affordances for Category-Level Robotic Manipulationcited by 152
  3. 2018Dense Object Nets: Learning Dense Visual Object Descriptors By and For Robotic Manipulationcited by 140
  4. 2019Unsupervised Learning of Object Keypoints for Perception and Controlcited by 109
  5. 2019Self-Supervised Correspondence in Visuomotor Policy Learningcited by 106
  6. 2019Imitation Learning from Observations by Minimizing Inverse Dynamics Disagreementcited by 46
  7. 2022Equivariant Transporter Networkcited by 44
  8. 2021AMP: Adversarial Motion Priors for Stylized Physics-Based Character Controlcited by 18
  9. 2017Optimization Beyond the Convolution: Generalizing Spatial Relations with End-to-End Metric Learningcited by 4

Built on by

Not cited yet.

Similar, not cited

Close in wording, no citation either way

  1. 2023A Reinforcement Learning Approach for Robotic Unloading from Visual Observations
  2. 2024Learning Transparent Reward Models via Unsupervised Feature Selection
  3. 2024Reward Machine Inference for Robotic Manipulation
  4. 2022Reinforcement learning with Demonstrations from Mismatched Task under Sparse Reward
  5. 2019Learning to Reach Goals via Iterated Supervised Learning
  6. 2019Positive-Unlabeled Reward Learning
  7. 2019Scaling data-driven robotics with reward sketching and batch reinforcement learning
  8. 2024Learning Manipulation Skills through Robot Chain-of-Thought with Sparse Failure Guidance