Localized active learning of Gaussian process state space models
- URL: http://arxiv.org/abs/2005.02191v3
- Date: Tue, 9 Jun 2020 19:57:11 GMT
- Title: Localized active learning of Gaussian process state space models
- Authors: Alexandre Capone, Jonas Umlauft, Thomas Beckers, Armin Lederer, Sandra
Hirche
- Abstract summary: A globally accurate model is not required to achieve good performance in many common control applications.
We propose an active learning strategy for Gaussian process state space models that aims to obtain an accurate model on a bounded subset of the state-action space.
By employing model predictive control, the proposed technique integrates information collected during exploration and adaptively improves its exploration strategy.
- Score: 63.97366815968177
- License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
- Abstract: The performance of learning-based control techniques crucially depends on how
effectively the system is explored. While most exploration techniques aim to
achieve a globally accurate model, such approaches are generally unsuited for
systems with unbounded state spaces. Furthermore, a globally accurate model is
not required to achieve good performance in many common control applications,
e.g., local stabilization tasks. In this paper, we propose an active learning
strategy for Gaussian process state space models that aims to obtain an
accurate model on a bounded subset of the state-action space. Our approach aims
to maximize the mutual information of the exploration trajectories with respect
to a discretization of the region of interest. By employing model predictive
control, the proposed technique integrates information collected during
exploration and adaptively improves its exploration strategy. To enable
computational tractability, we decouple the choice of most informative data
points from the model predictive control optimization step. This yields two
optimization problems that can be solved in parallel. We apply the proposed
method to explore the state space of various dynamical systems and compare our
approach to a commonly used entropy-based exploration strategy. In all
experiments, our method yields a better model within the region of interest
than the entropy-based method.
Related papers
- Recursive Gaussian Process State Space Model [4.572915072234487]
We propose a new online GPSSM method with adaptive capabilities for both operating domains and GP hyper parameters.
Online selection algorithm for inducing points is developed based on informative criteria to achieve lightweight learning.
Comprehensive evaluations on both synthetic and real-world datasets demonstrate the superior accuracy, computational efficiency, and adaptability of our method.
arXiv Detail & Related papers (2024-11-22T02:22:59Z) - Model-Free Active Exploration in Reinforcement Learning [53.786439742572995]
We study the problem of exploration in Reinforcement Learning and present a novel model-free solution.
Our strategy is able to identify efficient policies faster than state-of-the-art exploration approaches.
arXiv Detail & Related papers (2024-06-30T19:00:49Z) - The CAST package for training and assessment of spatial prediction models in R [0.0]
We introduce the CAST package and its core functionalities.
We will go through the different steps of the modelling workflow and show how CAST can be used to support more reliable spatial predictions.
arXiv Detail & Related papers (2024-04-10T12:48:10Z) - 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) - Reparameterized Policy Learning for Multimodal Trajectory Optimization [61.13228961771765]
We investigate the challenge of parametrizing policies for reinforcement learning in high-dimensional continuous action spaces.
We propose a principled framework that models the continuous RL policy as a generative model of optimal trajectories.
We present a practical model-based RL method, which leverages the multimodal policy parameterization and learned world model.
arXiv Detail & Related papers (2023-07-20T09:05:46Z) - Optimistic Active Exploration of Dynamical Systems [52.91573056896633]
We develop an algorithm for active exploration called OPAX.
We show how OPAX can be reduced to an optimal control problem that can be solved at each episode.
Our experiments show that OPAX is not only theoretically sound but also performs well for zero-shot planning on novel downstream tasks.
arXiv Detail & Related papers (2023-06-21T16:26:59Z) - FLEX: an Adaptive Exploration Algorithm for Nonlinear Systems [6.612035830987298]
We introduce FLEX, an exploration algorithm for nonlinear dynamics based on optimal experimental design.
Our policy maximizes the information of the next step and results in an adaptive exploration algorithm.
The performance achieved by FLEX is competitive and its computational cost is low.
arXiv Detail & Related papers (2023-04-26T10:20:55Z) - Partitioned Active Learning for Heterogeneous Systems [5.331649110169476]
We propose the partitioned active learning strategy established upon partitioned GP (PGP) modeling.
Global searching scheme accelerates the exploration aspect of active learning.
Local searching exploits the active learning criterion induced by the local GP model.
arXiv Detail & Related papers (2021-05-14T02:05:31Z) - Chance-Constrained Trajectory Optimization for Safe Exploration and
Learning of Nonlinear Systems [81.7983463275447]
Learning-based control algorithms require data collection with abundant supervision for training.
We present a new approach for optimal motion planning with safe exploration that integrates chance-constrained optimal control with dynamics learning and feedback control.
arXiv Detail & Related papers (2020-05-09T05:57:43Z)
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.