Flow-based Domain Randomization for Learning and Sequencing Robotic Skills

• URL: http://arxiv.org/abs/2502.01800v1
• Date: Mon, 03 Feb 2025 20:25:50 GMT
• Title: Flow-based Domain Randomization for Learning and Sequencing Robotic Skills
• Authors: Aidan Curtis, Eric Li, Michael Noseworthy, Nishad Gothoskar, Sachin Chitta, Hui Li, Leslie Pack Kaelbling, Nicole Carey,
• Abstract summary: Domain randomization in reinforcement learning is an established technique for increasing the robustness of control policies trained in simulation. In this paper we investigate automatically discovering a sampling distribution via entropy-regularized reward of a neural sampling distribution. We show that this architecture is more flexible than existing approaches that learn simpler, parameterized sampling distributions.
• Score: 24.17247101490744
• License:
• Abstract: Domain randomization in reinforcement learning is an established technique for increasing the robustness of control policies trained in simulation. By randomizing environment properties during training, the learned policy can become robust to uncertainties along the randomized dimensions. While the environment distribution is typically specified by hand, in this paper we investigate automatically discovering a sampling distribution via entropy-regularized reward maximization of a normalizing-flow-based neural sampling distribution. We show that this architecture is more flexible and provides greater robustness than existing approaches that learn simpler, parameterized sampling distributions, as demonstrated in six simulated and one real-world robotics domain. Lastly, we explore how these learned sampling distributions, combined with a privileged value function, can be used for out-of-distribution detection in an uncertainty-aware multi-step manipulation planner.

Related papers

• Enhanced Importance Sampling through Latent Space Exploration in Normalizing Flows [69.8873421870522]
  importance sampling is a rare event simulation technique used in Monte Carlo simulations. We propose a method for more efficient sampling by updating the proposal distribution in the latent space of a normalizing flow.
  arXiv  Detail & Related papers  (2025-01-06T21:18:02Z)
• Sampling for Model Predictive Trajectory Planning in Autonomous Driving using Normalizing Flows [1.2972104025246092]
  This paper investigates several sampling approaches for trajectory generation. normalizing flows originating from the field of variational inference are considered. Learning-based normalizing flow models are trained for a more efficient exploration of the input domain.
  arXiv  Detail & Related papers  (2024-04-15T10:45:12Z)
• Distributionally Robust Model-based Reinforcement Learning with Large State Spaces [55.14361269378122]
  Three major challenges in reinforcement learning are the complex dynamical systems with large state spaces, the costly data acquisition processes, and the deviation of real-world dynamics from the training environment deployment. We study distributionally robust Markov decision processes with continuous state spaces under the widely used Kullback-Leibler, chi-square, and total variation uncertainty sets. We propose a model-based approach that utilizes Gaussian Processes and the maximum variance reduction algorithm to efficiently learn multi-output nominal transition dynamics.
  arXiv  Detail & Related papers  (2023-09-05T13:42:11Z)
• Accurate generation of stochastic dynamics based on multi-model Generative Adversarial Networks [0.0]
  Generative Adversarial Networks (GANs) have shown immense potential in fields such as text and image generation. Here we quantitatively test this approach by applying it to a prototypical process on a lattice. Importantly, the discreteness of the model is retained despite the noise.
  arXiv  Detail & Related papers  (2023-05-25T10:41:02Z)
• Distributional GFlowNets with Quantile Flows [73.73721901056662]
  Generative Flow Networks (GFlowNets) are a new family of probabilistic samplers where an agent learns a policy for generating complex structure through a series of decision-making steps. In this work, we adopt a distributional paradigm for GFlowNets, turning each flow function into a distribution, thus providing more informative learning signals during training. Our proposed textitquantile matching GFlowNet learning algorithm is able to learn a risk-sensitive policy, an essential component for handling scenarios with risk uncertainty.
  arXiv  Detail & Related papers  (2023-02-11T22:06:17Z)
• Diverse Human Motion Prediction via Gumbel-Softmax Sampling from an Auxiliary Space [34.83587750498361]
  Diverse human motion prediction aims at predicting multiple possible future pose sequences from a sequence of observed poses. Previous approaches usually employ deep generative networks to model the conditional distribution of data, and then randomly sample outcomes from the distribution. We propose a novel sampling strategy for sampling very diverse results from an imbalanced multimodal distribution.
  arXiv  Detail & Related papers  (2022-07-15T09:03:57Z)
• Generative Adversarial Network for Probabilistic Forecast of Random Dynamical System [19.742888499307178]
  We present a deep learning model for data-driven simulations of random dynamical systems without a distributional assumption. We propose a regularization strategy for a generative adversarial network based on consistency conditions for the sequential inference problems. The behavior of the proposed model is studied by using three processes with complex noise structures.
  arXiv  Detail & Related papers  (2021-11-04T19:50:56Z)
• Pre-training of Deep RL Agents for Improved Learning under Domain Randomization [63.09932240840656]
  We show how to pre-train a perception encoder that already provides an embedding invariant to the randomization. We demonstrate this yields consistently improved results on a randomized version of DeepMind control suite tasks and a stacking environment on arbitrary backgrounds with zero-shot transfer to a physical robot.
  arXiv  Detail & Related papers  (2021-04-29T14:54:11Z)
• Goal-oriented adaptive sampling under random field modelling of response probability distributions [0.6445605125467573]
  We consider cases where the spatial variation of response distributions does not only concern their mean and/or variance but also other features including for instance shape or uni-modality versus multi-modality. Our contributions build upon a non-parametric Bayesian approach to modelling the thereby induced fields of probability distributions.
  arXiv  Detail & Related papers  (2021-02-15T15:55:23Z)
• Guided Uncertainty-Aware Policy Optimization: Combining Learning and Model-Based Strategies for Sample-Efficient Policy Learning [75.56839075060819]
  Traditional robotic approaches rely on an accurate model of the environment, a detailed description of how to perform the task, and a robust perception system to keep track of the current state. reinforcement learning approaches can operate directly from raw sensory inputs with only a reward signal to describe the task, but are extremely sample-inefficient and brittle. In this work, we combine the strengths of model-based methods with the flexibility of learning-based methods to obtain a general method that is able to overcome inaccuracies in the robotics perception/actuation pipeline.
  arXiv  Detail & Related papers  (2020-05-21T19:47:05Z)
• Spatially Adaptive Inference with Stochastic Feature Sampling and Interpolation [72.40827239394565]
  We propose to compute features only at sparsely sampled locations. We then densely reconstruct the feature map with an efficient procedure. The presented network is experimentally shown to save substantial computation while maintaining accuracy over a variety of computer vision tasks.
  arXiv  Detail & Related papers  (2020-03-19T15:36:31Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.