mlsanityData to 14 Oct 2026

MORPH: Design Co-optimization with Reinforcement Learning via a Differentiable Hardware Model Proxy

arXiv 2309.17227 ↗First posted 29 Sep 2023cs.RO cs.AI cs.LGcited by 8

Not on the map. Why?

Abstract (arXiv)

We introduce MORPH, a method for co-optimization of hardware design parameters and control policies in simulation using reinforcement learning. Like most co-optimization methods, MORPH relies on a model of the hardware being optimized, usually simulated based on the laws of physics. However, such a model is often difficult to integrate into an effective optimization routine. To address this, we introduce a proxy hardware model, which is always differentiable and enables efficient co-optimization alongside a long-horizon control policy using RL. MORPH is designed to ensure that the optimized hardware proxy remains as close as possible to its realistic counterpart, while still enabling task completion. We demonstrate our approach on simulated 2D reaching and 3D multi-fingered manipulation tasks.

Key facts. Cited by 8 papers in the map (data through 14 Oct 2026). Builds on 16 of its 27 references that are in the map. First posted on arXiv 29 Sep 2023.

Builds on

16 of 27 references.

References · 16

  1. 2017Multi-Task Learning Using Uncertainty to Weigh Losses for Scene Geometry and Semanticscited by 1,358
  2. 2020Gradient Surgery for Multi-Task Learningcited by 1,256
  3. 2017GradNorm: Gradient Normalization for Adaptive Loss Balancing in Deep Multitask Networkscited by 834
  4. 2018Multi-Task Learning as Multi-Objective Optimizationcited by 821
  5. 2018Multi-task Deep Reinforcement Learning with PopArtcited by 141
  6. 2018Reinforcement Learning for Improving Agent Designcited by 56
  7. 2018Jointly Learning to Construct and Control Agents using Deep Reinforcement Learningcited by 55
  8. 2021An End-to-End Differentiable Framework for Contact-Aware Robot Designcited by 54
  9. 2017Scalable Co-Optimization of Morphology and Control in Embodied Machinescited by 40
  10. 2021Transform2Act: Learning a Transform-and-Control Policy for Efficient Agent Designcited by 38
  11. 2019Data-efficient Co-Adaptation of Morphology and Behaviour with Deep Reinforcement Learningcited by 37
  12. 2020Hardware as Policy: Mechanical and Computational Co-Optimization using Deep Reinforcement Learningcited by 32
4 more
  1. 2019Data-efficient Learning of Morphology and Controller for a Microrobotcited by 26
  2. 2021Multi-Objective Graph Heuristic Search for Terrestrial Robot Designcited by 20
  3. 2020Learning Directed Locomotion in Modular Robots with Evolvable Morphologiescited by 19
  4. 2018Real-World Evolution Adapts Robot Morphology and Control to Hardware Limitationscited by 5

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2024: 1; 2025: 2; 2026: 5.

8 papers.

  1. 2025VLMgineer: Vision Language Models as Robotic Toolsmithscited by 10
  2. 2024Text2Robot: Evolutionary Robot Design from Text Descriptionscited by 8
  3. 2025Embodied Co-Design for Rapidly Evolving Agents: Taxonomy, Frontiers, and Challengescited by 4
  4. 2026Latent Diffeomorphic Co-Design of End-Effectors for Deformable and Fragile Object Manipulationcited by 1
  5. 2026RobotDesignGPT: Automated Robot Design Synthesis using Vision Language Modelscited by 0
  6. 2026LEGO: Latent-space Exploration for Geometry-aware Optimization of Humanoid Kinematic Designcited by 0
  7. 2026Differentiable Multiphysics Co-Optimization via Implicit Neural Representations: A Transient Hamburger-Cooking Benchmarkcited by 0
  8. 2026Environment Parameter Gradient Theorem for Co-Design in Reinforcement Learningcited by 0