mlsanityData to 7 Oct 2026

Adaptive Asynchronous Control Using Meta-learned Neural Ordinary Differential Equations

arXiv 2207.12062 ↗First posted 25 Jul 2022cs.LG cs.ROcited by 2

Not on the map. Why?

Abstract (arXiv)

Model-based Reinforcement Learning and Control have demonstrated great potential in various sequential decision making problem domains, including in robotics settings. However, real-world robotics systems often present challenges that limit the applicability of those methods. In particular, we note two problems that jointly happen in many industrial systems: 1) Irregular/asynchronous observations and actions and 2) Dramatic changes in environment dynamics from an episode to another (e.g. varying payload inertial properties). We propose a general framework that overcomes those difficulties by meta-learning adaptive dynamics models for continuous-time prediction and control. The proposed approach is task-agnostic and can be adapted to new tasks in a straight-forward manner. We present evaluations in two different robot simulations and on a real industrial robot.

Key facts. Cited by 2 papers in the map (data through 7 Oct 2026). Builds on 36 of its 61 references that are in the map. First posted on arXiv 25 Jul 2022.

Builds on

36 of 61 references.

References · 36

  1. 2017Model-Agnostic Meta-Learning for Fast Adaptation of Deep Networkscited by 4,861
  2. 2018Neural Ordinary Differential Equationscited by 3,733
  3. 2016Matching Networks for One Shot Learningcited by 2,246
  4. 2018Learning Latent Dynamics for Planning from Pixelscited by 1,221
  5. 2020Meta-Learning in Neural Networks: A Surveycited by 944
  6. 2018Deep Reinforcement Learning in a Handful of Trials using Probabilistic Dynamics Modelscited by 748
  7. 2019Solving Rubik's Cube with a Robot Handcited by 699
  8. 2017Evolution Strategies as a Scalable Alternative to Reinforcement Learningcited by 555
  9. 2019Model-Based Reinforcement Learning for Ataricited by 495
  10. 2016RL2: Fast Reinforcement Learning via Slow Reinforcement Learningcited by 490
  11. 2021RMA: Rapid Motor Adaptation for Legged Robotscited by 430
  12. 2020Sim-to-Real Transfer in Deep Reinforcement Learning for Robotics: a Surveycited by 388
24 more
  1. 2016Learning Hand-Eye Coordination for Robotic Grasping with Deep Learning and Large-Scale Data Collectioncited by 312
  2. 2017Neural Network Dynamics for Model-Based Deep Reinforcement Learning with Model-Free Fine-Tuningcited by 288
  3. 2018Learning to Adapt in Dynamic, Real-World Environments Through Meta-Reinforcement Learningcited by 270
  4. 2018Meta-Gradient Reinforcement Learningcited by 156
  5. 2020Sample-efficient Cross-Entropy Method for Real-time Planningcited by 90
  6. 2020Learning Differential Equations that are Easy to Solvecited by 81
  7. 2020Discovering Reinforcement Learning Algorithmscited by 75
  8. 2019ES-MAML: Simple Hessian-Free Meta Learningcited by 57
  9. 2019Making Deep Q-learning methods robust to time discretizationcited by 51
  10. 2021Continuous-Time Model-Based Reinforcement Learningcited by 39
  11. 2021Adaptive-Control-Oriented Meta-Learning for Nonlinear Systemscited by 38
  12. 2020Hypersolvers: Toward Fast Continuous-Depth Modelscited by 33
  13. 2020Model-based Reinforcement Learning for Semi-Markov Decision Processes with Neural ODEscited by 32
  14. 2020Model-Based Meta-Reinforcement Learning for Flight with Suspended Payloadscited by 27
  15. 2021KNODE-MPC: A Knowledge-based Data-driven Predictive Control Framework for Aerial Robotscited by 26
  16. 2021Dynamics-Aware Quality-Diversity for Efficient Learning of Skill Repertoirescited by 20
  17. 2022Control-oriented meta-learningcited by 17
  18. 2022Online Dynamics Learning for Predictive Control with an Application to Aerial Robotscited by 17
  19. 2022Physics-Inspired Temporal Learning of Quadrotor Dynamics for Accurate Model Predictive Trajectory Trackingcited by 16
  20. 2020Sim-to-Real Transfer with Incremental Environment Complexity for Reinforcement Learning of Depth-Based Robot Navigationcited by 13
  21. 2019From exploration to control: learning object manipulation skills through novelty search and local adaptationcited by 12
  22. 2021Accelerating Neural ODEs Using Model Order Reductioncited by 9
  23. 2021Few-shot Quality-Diversity Optimizationcited by 8
  24. 2020LBGP: Learning Based Goal Planning for Autonomous Following in Frontcited by 4

Built on by

Cited by year

Citing papers per year: 2023: 1; 2024: 1.

2 papers.

  1. 2024Learning Adaptive Hydrodynamic Models Using Neural ODEs in Complex Conditionscited by 3
  2. 2023Data-efficient, Explainable and Safe Box Manipulation: Illustrating the Advantages of Physical Priors in Model-Predictive Controlcited by 0