mlsanityData to 7 Oct 2026

Malleable Agents for Re-Configurable Robotic Manipulators

arXiv 2202.02395 ↗First posted 4 Feb 2022cs.RO cs.AIcited by 0

Not on the map. Why?

Abstract (arXiv)

Re-configurable robots have more utility and flexibility for many real-world tasks. Designing a learning agent to operate such robots requires adapting to different configurations. Here, we focus on robotic arms with multiple rigid links connected by joints. We propose a deep reinforcement learning agent with sequence neural networks embedded in the agent to adapt to robotic arms that have a varying number of links. Further, with the additional tool of domain randomization, this agent adapts to different configurations. We perform simulations on a 2D N-link arm to show the ability of our network to transfer and generalize efficiently.

Key facts. No citing papers in the map yet (data through 7 Oct 2026). Builds on 25 of its 44 references that are in the map. First posted on arXiv 4 Feb 2022.

Builds on

25 of 44 references.

References · 25

  1. 2018Soft Actor-Critic: Off-Policy Maximum Entropy Deep Reinforcement Learning with a Stochastic Actorcited by 4,635
  2. 2014Learning Phrase Representations using RNN Encoder-Decoder for Statistical Machine Translationcited by 4,016
  3. 2017Domain Randomization for Transferring Deep Neural Networks from Simulation to the Real Worldcited by 1,401
  4. 2017Adversarial Discriminative Domain Adaptationcited by 1,309
  5. 2018Soft Actor-Critic Algorithms and Applicationscited by 1,179
  6. 2018QT-Opt: Scalable Deep Reinforcement Learning for Vision-Based Robotic Manipulationcited by 730
  7. 2017Learning Complex Dexterous Manipulation with Deep Reinforcement Learning and Demonstrationscited by 685
  8. 2018Learning Dexterous In-Hand Manipulationcited by 643
  9. 2016Deep Reinforcement Learning for Robotic Manipulation with Asynchronous Off-Policy Updatescited by 342
  10. 2017DARLA: Improving Zero-Shot Transfer in Reinforcement Learningcited by 147
  11. 2018Reinforcement and Imitation Learning for Diverse Visuomotor Skillscited by 124
  12. 2020One Policy to Control Them All: Shared Modular Policies for Agent-Agnostic Controlcited by 114
13 more
  1. 2016Sim-to-Real Robot Learning from Pixels with Progressive Netscited by 89
  2. 2017Learning Invariant Feature Spaces to Transfer Skills with Reinforcement Learningcited by 84
  3. 2018Reinforcement Learning from Imperfect Demonstrationscited by 74
  4. 2018Composable Deep Reinforcement Learning for Robotic Manipulationcited by 70
  5. 2019Learning to Control Self-Assembling Morphologies: A Study of Generalization via Modularitycited by 68
  6. 2020My Body is a Cage: the Role of Morphology in Graph-Based Incompatible Controlcited by 68
  7. 2018Jointly Learning to Construct and Control Agents using Deep Reinforcement Learningcited by 51
  8. 2018Hardware Conditioned Policies for Multi-Robot Transfer Learningcited by 42
  9. 2016Learning Dexterous Manipulation for a Soft Robotic Hand from Human Demonstrationcited by 35
  10. 2021Domain Adaptation In Reinforcement Learning Via Latent Unified State Representationcited by 33
  11. 2016Learning Dexterous Manipulation Policies from Experience and Imitationcited by 32
  12. 2015Attend, Adapt and Transfer: Attentive Deep Architecture for Adaptive Transfer from multiple sources in the same domaincited by 19
  13. 2021Learning Modular Robot Control Policiescited by 18

Built on by

Not cited yet.