Cost-Driven Representation Learning for Linear Quadratic Gaussian Control: Part II

• URL: http://arxiv.org/abs/2603.07437v1
• Date: Sun, 08 Mar 2026 03:20:52 GMT
• Title: Cost-Driven Representation Learning for Linear Quadratic Gaussian Control: Part II
• Abstract summary: We study the problem of state representation learning for control from partial and potentially high-dimensional observations.<n>We approach this problem via cost-driven state representation learning, in which we learn a dynamical model in a latent state space by predicting cumulative costs.
• Score: 57.29427648134142
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: We study the problem of state representation learning for control from partial and potentially high-dimensional observations. We approach this problem via cost-driven state representation learning, in which we learn a dynamical model in a latent state space by predicting cumulative costs. In particular, we establish finite-sample guarantees on finding a near-optimal representation function and a near-optimal controller using the learned latent model for infinite-horizon time-invariant Linear Quadratic Gaussian (LQG) control. We study two approaches to cost-driven representation learning, which differ in whether the transition function of the latent state is learned explicitly or implicitly. The first approach has also been investigated in Part I of this work, for finite-horizon time-varying LQG control. The second approach closely resembles MuZero, a recent breakthrough in empirical reinforcement learning, in that it learns latent dynamics implicitly by predicting cumulative costs. A key technical contribution of this Part II is to prove persistency of excitation for a new stochastic process that arises from the analysis of quadratic regression in our approach, and may be of independent interest.

Related papers

• Q-Measure-Learning for Continuous State RL: Efficient Implementation and Convergence [10.189658648290257]
  We study reinforcement learning in infinite-horizon discounted Markov decision processes with continuous state spaces.<n>We propose the novel Q-Measure-Learning, which learns a signed empirical measure supported on visited state-action pairs.
  arXiv  Detail & Related papers  (2026-03-03T21:15:22Z)
• Sublinear Regret for a Class of Continuous-Time Linear-Quadratic Reinforcement Learning Problems [10.404992912881601]
  We study reinforcement learning (RL) for a class of continuous-time linear-quadratic (LQ) control problems for diffusions.<n>We apply a model-free approach that relies neither on knowledge of model parameters nor on their estimations, and devise an RL algorithm to learn the optimal policy parameter directly.
  arXiv  Detail & Related papers  (2024-07-24T12:26:21Z)
• Cost-Driven Representation Learning for Linear Quadratic Gaussian Control: Part I [57.29427648134142]
  We study the task of learning state representations from potentially high-dimensional observations.<n>We pursue a cost-driven approach, where a dynamic model in some latent state space is learned by predicting the costs without predicting the observations or actions.
  arXiv  Detail & Related papers  (2022-12-30T01:42:04Z)
• Beyond the Edge of Stability via Two-step Gradient Updates [49.03389279816152]
  Gradient Descent (GD) is a powerful workhorse of modern machine learning. GD's ability to find local minimisers is only guaranteed for losses with Lipschitz gradients. This work focuses on simple, yet representative, learning problems via analysis of two-step gradient updates.
  arXiv  Detail & Related papers  (2022-06-08T21:32:50Z)
• Embed to Control Partially Observed Systems: Representation Learning with Provable Sample Efficiency [105.17746223041954]
  Reinforcement learning in partially observed Markov decision processes (POMDPs) faces two challenges. It often takes the full history to predict the future, which induces a sample complexity that scales exponentially with the horizon. We propose a reinforcement learning algorithm named Embed to Control (ETC), which learns the representation at two levels while optimizing the policy.
  arXiv  Detail & Related papers  (2022-05-26T16:34:46Z)
• Efficient Performance Bounds for Primal-Dual Reinforcement Learning from Demonstrations [1.0609815608017066]
  We consider large-scale Markov decision processes with an unknown cost function and address the problem of learning a policy from a finite set of expert demonstrations. Existing inverse reinforcement learning methods come with strong theoretical guarantees, but are computationally expensive. We introduce a novel bilinear saddle-point framework using Lagrangian duality to bridge the gap between theory and practice.
  arXiv  Detail & Related papers  (2021-12-28T05:47:24Z)
• Adaptive Control and Regret Minimization in Linear Quadratic Gaussian (LQG) Setting [91.43582419264763]
  We propose LqgOpt, a novel reinforcement learning algorithm based on the principle of optimism in the face of uncertainty. LqgOpt efficiently explores the system dynamics, estimates the model parameters up to their confidence interval, and deploys the controller of the most optimistic model.
  arXiv  Detail & Related papers  (2020-03-12T19:56:38Z)
• Upper Confidence Primal-Dual Reinforcement Learning for CMDP with Adversarial Loss [145.54544979467872]
  We consider online learning for episodically constrained Markov decision processes (CMDPs) We propose a new emphupper confidence primal-dual algorithm, which only requires the trajectories sampled from the transition model. Our analysis incorporates a new high-probability drift analysis of Lagrange multiplier processes into the celebrated regret analysis of upper confidence reinforcement learning.
  arXiv  Detail & Related papers  (2020-03-02T05:02:23Z)

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.