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

• URL: http://arxiv.org/abs/2212.14511v3
• Date: Wed, 03 Sep 2025 03:48:44 GMT
• Title: Cost-Driven Representation Learning for Linear Quadratic Gaussian Control: Part I
• Authors: Yi Tian, Kaiqing Zhang, Russ Tedrake, Suvrit Sra,
• Abstract summary: 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.
• Score: 57.29427648134142
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: We study the task of learning state representations from potentially high-dimensional observations, with the goal of controlling an unknown partially observable system. 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. In particular, we focus on an intuitive cost-driven state representation learning method for solving Linear Quadratic Gaussian (LQG) control, one of the most fundamental partially observable control problems. As our main results, we establish finite-sample guarantees of finding a near-optimal state representation function and a near-optimal controller using the directly learned latent model, for finite-horizon time-varying LQG control problems. To the best of our knowledge, despite various empirical successes, finite-sample guarantees of such a cost-driven approach remain elusive. Our result underscores the value of predicting multi-step costs, an idea that is key to our theory, and notably also an idea that is known to be empirically valuable for learning state representations. A second part of this work, that is to appear as Part II, addresses the infinite-horizon linear time-invariant setting; it also extends the results to an approach that implicitly learns the latent dynamics, inspired by the recent empirical breakthrough of MuZero in model-based reinforcement learning.

Related papers

• Model-free Methods for Event History Analysis and Efficient Adjustment (PhD Thesis) [55.2480439325792]
  This thesis is a series of independent contributions to statistics unified by a model-free perspective. The first chapter elaborates on how a model-free perspective can be used to formulate flexible methods that leverage prediction techniques from machine learning. The second chapter studies the concept of local independence, which describes whether the evolution of one process is directly influenced by another.
  arXiv  Detail & Related papers  (2025-02-11T19:24:09Z)
• Sublinear Regret for a Class of Continuous-Time Linear--Quadratic Reinforcement Learning Problems [10.404992912881601]
  We study reinforcement learning for a class of continuous-time linear-quadratic (LQ) control problems for diffusions. We apply a model-free approach that relies neither on knowledge of model parameters nor on their estimations, and devise an actor-critic algorithm to learn the optimal policy parameter directly.
  arXiv  Detail & Related papers  (2024-07-24T12:26:21Z)
• Unlearning with Control: Assessing Real-world Utility for Large Language Model Unlearning [97.2995389188179]
  Recent research has begun to approach large language models (LLMs) unlearning via gradient ascent (GA) Despite their simplicity and efficiency, we suggest that GA-based methods face the propensity towards excessive unlearning. We propose several controlling methods that can regulate the extent of excessive unlearning.
  arXiv  Detail & Related papers  (2024-06-13T14:41:00Z)
• Getting More Juice Out of the SFT Data: Reward Learning from Human Demonstration Improves SFT for LLM Alignment [65.15914284008973]
  We propose to leverage an Inverse Reinforcement Learning (IRL) technique to simultaneously build an reward model and a policy model. We show that the proposed algorithms converge to the stationary solutions of the IRL problem. Our results indicate that it is beneficial to leverage reward learning throughout the entire alignment process.
  arXiv  Detail & Related papers  (2024-05-28T07:11:05Z)
• Stable Inverse Reinforcement Learning: Policies from Control Lyapunov Landscapes [4.229902091180109]
  We propose a novel, stability-certified IRL approach to learning control Lyapunov functions from demonstrations data. By exploiting closed-form expressions for associated control policies, we are able to efficiently search the space of CLFs. We present a theoretical analysis of the optimality properties provided by the CLF and evaluate our approach using both simulated and real-world data.
  arXiv  Detail & Related papers  (2024-05-14T16:40:45Z)
• Learning Interpretable Policies in Hindsight-Observable POMDPs through Partially Supervised Reinforcement Learning [57.67629402360924]
  We introduce the Partially Supervised Reinforcement Learning (PSRL) framework. At the heart of PSRL is the fusion of both supervised and unsupervised learning. We show that PSRL offers a potent balance, enhancing model interpretability while preserving, and often significantly outperforming, the performance benchmarks set by traditional methods.
  arXiv  Detail & Related papers  (2024-02-14T16:23:23Z)
• An Information Theoretic Approach to Machine Unlearning [45.600917449314444]
  Key challenge in unlearning is forgetting the necessary data in a timely manner, while preserving model performance. In this work, we address the zero-shot unlearning scenario, whereby an unlearning algorithm must be able to remove data given only a trained model and the data to be forgotten. We derive a simple but principled zero-shot unlearning method based on the geometry of the model.
  arXiv  Detail & Related papers  (2024-02-02T13:33:30Z)
• Flow-based Recurrent Belief State Learning for POMDPs [20.860726518161204]
  Partially Observable Markov Decision Process (POMDP) provides a principled and generic framework to model real world sequential decision making processes. The main challenge lies in how to accurately obtain the belief state, which is the probability distribution over the unobservable environment states. Recent advances in deep learning techniques show great potential to learn good belief states.
  arXiv  Detail & Related papers  (2022-05-23T05:29:55Z)
• Masked prediction tasks: a parameter identifiability view [49.533046139235466]
  We focus on the widely used self-supervised learning method of predicting masked tokens. We show that there is a rich landscape of possibilities, out of which some prediction tasks yield identifiability, while others do not.
  arXiv  Detail & Related papers  (2022-02-18T17:09:32Z)
• 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)
• Improving Self-supervised Learning with Automated Unsupervised Outlier Arbitration [83.29856873525674]
  We introduce a lightweight latent variable model UOTA, targeting the view sampling issue for self-supervised learning. Our method directly generalizes to many mainstream self-supervised learning approaches.
  arXiv  Detail & Related papers  (2021-12-15T14:05:23Z)
• A Free Lunch from the Noise: Provable and Practical Exploration for Representation Learning [55.048010996144036]
  We show that under some noise assumption, we can obtain the linear spectral feature of its corresponding Markov transition operator in closed-form for free. We propose Spectral Dynamics Embedding (SPEDE), which breaks the trade-off and completes optimistic exploration for representation learning by exploiting the structure of the noise.
  arXiv  Detail & Related papers  (2021-11-22T19:24:57Z)
• Dream to Explore: Adaptive Simulations for Autonomous Systems [3.0664963196464448]
  We tackle the problem of learning to control dynamical systems by applying Bayesian nonparametric methods. By employing Gaussian processes to discover latent world dynamics, we mitigate common data efficiency issues observed in reinforcement learning. Our algorithm jointly learns a world model and policy by optimizing a variational lower bound of a log-likelihood.
  arXiv  Detail & Related papers  (2021-10-27T04:27:28Z)
• 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)
• Value-driven Hindsight Modelling [68.658900923595]
  Value estimation is a critical component of the reinforcement learning (RL) paradigm. Model learning can make use of the rich transition structure present in sequences of observations, but this approach is usually not sensitive to the reward function. We develop an approach for representation learning in RL that sits in between these two extremes. This provides tractable prediction targets that are directly relevant for a task, and can thus accelerate learning the value function.
  arXiv  Detail & Related papers  (2020-02-19T18:10:20Z)

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.