mlsanityData to 7 Oct 2026

Composite Gaussian Processes Flows for Learning Discontinuous Multimodal Policies

arXiv 2502.01913 ↗First posted 4 Feb 2025cs.RO cs.LGcited by 0

Not on the map. Why?

Abstract (arXiv)

Learning control policies for real-world robotic tasks often involve challenges such as multimodality, local discontinuities, and the need for computational efficiency. These challenges arise from the complexity of robotic environments, where multiple solutions may coexist. To address these issues, we propose Composite Gaussian Processes Flows (CGP-Flows), a novel semi-parametric model for robotic policy. CGP-Flows integrate Overlapping Mixtures of Gaussian Processes (OMGPs) with the Continuous Normalizing Flows (CNFs), enabling them to model complex policies addressing multimodality and local discontinuities. This hybrid approach retains the computational efficiency of OMGPs while incorporating the flexibility of CNFs. Experiments conducted in both simulated and real-world robotic tasks demonstrate that CGP-flows significantly improve performance in modeling control policies. In a simulation task, we confirmed that CGP-Flows had a higher success rate compared to the baseline method, and the success rate of GCP-Flow was significantly different from the success rate of other baselines in chi-square tests.

Key facts. No citing papers in the map yet (data through 7 Oct 2026). Builds on 14 of its 33 references that are in the map. First posted on arXiv 4 Feb 2025.

Builds on

14 of 33 references.

References · 14

  1. 2018Neural Ordinary Differential Equationscited by 3,733
  2. 2023Diffusion Policy: Visuomotor Policy Learning via Action Diffusioncited by 2,730
  3. 2019Normalizing Flows for Probabilistic Modeling and Inferencecited by 1,315
  4. 2017Sigmoid-Weighted Linear Units for Neural Network Function Approximation in Reinforcement Learningcited by 935
  5. 2017Generative Adversarial Networks: An Overviewcited by 588
  6. 2018FFJORD: Free-form Continuous Dynamics for Scalable Reversible Generative Modelscited by 584
  7. 2018An Algorithmic Perspective on Imitation Learningcited by 455
  8. 2017Multi-Modal Imitation Learning from Unstructured Demonstrations using Generative Adversarial Netscited by 64
  9. 2024Learning Robotic Manipulation Policies from Point Clouds with Conditional Flow Matchingcited by 63
  10. 2021Non-Gaussian Gaussian Processes for Few-Shot Regressioncited by 12
  11. 2022IL-flOw: Imitation Learning from Observation using Normalizing Flowscited by 12
  12. 2022Bayesian Disturbance Injection: Robust Imitation Learning of Flexible Policies for Robot Manipulationcited by 8
2 more
  1. 2021Variational Policy Search using Sparse Gaussian Process Priors for Learning Multimodal Optimal Actionscited by 3
  2. 2022Gaussian Process Self-triggered Policy Search in Weakly Observable Environmentscited by 1

Built on by

Not cited yet.