English
Related papers

Related papers: KL-learning: Online solution of Kullback-Leibler c…

200 papers

We reformulate a class of non-linear stochastic optimal control problems introduced by Todorov (2007) as a Kullback-Leibler (KL) minimization problem. As a result, the optimal control computation reduces to an inference computation and…

Optimization and Control · Mathematics 2012-01-19 B. Kappen , V. Gomez , M. Opper

This paper considers an online (real-time) control problem that involves an agent performing a discrete-time random walk over a finite state space. The agent's action at each time step is to specify the probability distribution for the next…

Optimization and Control · Mathematics 2014-01-15 Peng Guan , Maxim Raginsky , Rebecca Willett

Kullback-Leibler (KL) control enables efficient numerical methods for nonlinear optimal control problems. The crucial assumption of KL control is the full controllability of the transition distribution. However, this assumption is often…

Systems and Control · Electrical Eng. & Systems 2022-03-25 Kaito Ito , Kenji Kashima

Kullback Leibler (KL) control problems allow for efficient computation of optimal control by solving a principal eigenvector problem. However, direct applicability of such framework to continuous state-action systems is limited. In this…

Systems and Control · Computer Science 2014-08-28 Takamitsu Matsubara , Vicenç Gómez , Hilbert J. Kappen

We present two nonparametric approaches to Kullback-Leibler (KL) control, or linearly-solvable Markov decision problem (LMDP) based on Gaussian processes (GP) and Nystr\"{o}m approximation. Compared to recently developed parametric methods,…

Systems and Control · Computer Science 2016-06-17 Yunpeng Pan , Evangelos Theodorou

We consider the problem of stochastic optimal control, where the state-feedback control policies take the form of a probability distribution and where a penalty on the entropy is added. By viewing the cost function as a Kullback- Leibler…

Optimization and Control · Mathematics 2024-12-12 Marc Lambert , Francis Bach , Silvère Bonnabel

We consider model-based reinforcement learning in finite Markov De- cision Processes (MDPs), focussing on so-called optimistic strategies. In MDPs, optimism can be implemented by carrying out extended value it- erations under a constraint…

Machine Learning · Computer Science 2011-09-22 Sarah Filippi , Olivier Cappé , Aurélien Garivier

This paper proposes an agent-based optimistic policy iteration (OPI) scheme for learning stationary optimal stochastic policies in multi-agent Markov Decision Processes (MDPs), in which agents incur a Kullback-Leibler (KL) divergence cost…

Artificial Intelligence · Computer Science 2024-10-22 Khaled Nakhleh , Ceyhun Eksin , Sabit Ekin

This paper addresses a new interpretation of the traditional optimization method in reinforcement learning (RL) as optimization problems using reverse Kullback-Leibler (KL) divergence, and derives a new optimization method using forward KL…

Machine Learning · Computer Science 2022-04-25 Taisuke Kobayashi

Derivative based optimization methods are efficient at solving optimal control problems near local optima. However, their ability to converge halts when derivative information vanishes. The inference approach to optimal control does not…

Robotics · Computer Science 2022-03-01 Daniel Layeghi , Steve Tonneau , Michael Mistry

This paper presents approaches to mean-field control, motivated by distributed control of multi-agent systems. Control solutions are based on a convex optimization problem, whose domain is a convex set of probability mass functions (pmfs).…

Optimization and Control · Mathematics 2023-06-12 Neil Cammardella , Ana Bušić , Sean Meyn

Accelerated algorithms for maximum likelihood image reconstruction are essential for emerging applications such as 3D tomography, dynamic tomographic imaging, and other high dimensional inverse problems. In this paper, we introduce and…

Computation · Statistics 2012-01-31 Stéphane Chrétien , Alfred O. Hero

Sampling-based model predictive control (MPC) has the potential for use in a wide variety of robotic systems. However, its unstable updates and poor convergence render it unsuitable for real-time control of robotic systems. This study…

Robotics · Computer Science 2026-01-08 Taisuke Kobayashi , Kota Fukumoto

We consider Markov Decision Problems defined over continuous state and action spaces, where an autonomous agent seeks to learn a map from its states to actions so as to maximize its long-term discounted accumulation of rewards. We address…

Machine Learning · Computer Science 2018-04-23 Alec Koppel , Ekaterina Tolstaya , Ethan Stump , Alejandro Ribeiro

The objective in this paper is to obtain fast converging reinforcement learning algorithms to approximate solutions to the problem of discounted cost optimal stopping in an irreducible, uniformly ergodic Markov chain, evolving on a compact…

Systems and Control · Computer Science 2019-10-01 Shuhang Chen , Adithya M. Devraj , Ana Bušić , Sean P. Meyn

We study the estimation of risk-sensitive policies in reinforcement learning problems defined by a Markov Decision Process (MDPs) whose state and action spaces are countably finite. Prior efforts are predominately afflicted by computational…

Machine Learning · Statistics 2020-03-02 Junyu Zhang , Amrit Singh Bedi , Mengdi Wang , Alec Koppel

We study a Q learning algorithm for continuous time stochastic control problems. The proposed algorithm uses the sampled state process by discretizing the state and control action spaces under piece-wise constant control processes. We show…

Optimization and Control · Mathematics 2023-03-10 Erhan Bayraktar , Ali Devran Kara

Many of the recent trajectory optimization algorithms alternate between linear approximation of the system dynamics around the mean trajectory and conservative policy update. One way of constraining the policy change is by bounding the…

Machine Learning · Computer Science 2018-07-03 Riad Akrour , Abbas Abdolmaleki , Hany Abdulsamad , Jan Peters , Gerhard Neumann

In this paper, we provide a novel algorithm for solving planning and learning problems of Markov decision processes. The proposed algorithm follows a policy iteration-type update by using a rank-one approximation of the transition…

Optimization and Control · Mathematics 2025-10-23 Arman Sharifi Kolarijani , Tolga Ok , Peyman Mohajerin Esfahani , Mohamad Amin Sharif Kolarijani

We develop a stochastic approximation-type algorithm to solve finite state/action, infinite-horizon, risk-aware Markov decision processes. Our algorithm has two loops. The inner loop computes the risk by solving a stochastic saddle-point…

Optimization and Control · Mathematics 2019-12-05 Wenjie Huang , William B. Haskell
‹ Prev 1 2 3 10 Next ›