English
Related papers

Related papers: Dynamic Programming Through the Lens of Semismooth…

200 papers

Markov decision problems are most commonly solved via dynamic programming. Another approach is Bellman residual minimization, which directly minimizes the squared Bellman residual objective function. However, compared to dynamic…

Machine Learning · Computer Science 2026-04-28 Donghwan Lee , Hyukjun Yang

We propose a principled kernel-based policy iteration algorithm to solve the continuous-state Markov Decision Processes (MDPs). In contrast to most decision-theoretic planning frameworks, which assume fully known state transition models, we…

Robotics · Computer Science 2020-06-04 Junhong Xu , Kai Yin , Lantao Liu

Planning problems where effects of actions are non-deterministic can be modeled as Markov decision processes. Planning problems are usually goal-directed. This paper proposes several techniques for exploiting the goal-directedness to…

Artificial Intelligence · Computer Science 2013-02-08 Nevin Lianwen Zhang , Weihong Zhang

Value iteration is a fixed point iteration technique utilized to obtain the optimal value function and policy in a discounted reward Markov Decision Process (MDP). Here, a contraction operator is constructed and applied repeatedly to arrive…

Machine Learning · Computer Science 2021-09-21 Chandramouli Kamanchi , Raghuram Bharadwaj Diddigi , Shalabh Bhatnagar

Value iteration is a commonly used and empirically competitive method in solving many Markov decision process problems. However, it is known that value iteration has only pseudo-polynomial complexity in general. We establish a somewhat…

Artificial Intelligence · Computer Science 2013-01-07 Omid Madani

Dynamic programming is a class of algorithms used to compute optimal control policies for Markov decision processes. Dynamic programming is ubiquitous in control theory, and is also the foundation of reinforcement learning. In this paper,…

Category Theory · Mathematics 2023-08-01 Jules Hedges , Riu Rodríguez Sakamoto

We describe an approximate dynamic programming approach to compute lower bounds on the optimal value function for a discrete time, continuous space, infinite horizon setting. The approach iteratively constructs a family of lower bounding…

Systems and Control · Electrical Eng. & Systems 2024-12-20 Paul N. Beuchat , Joseph Warrington , John Lygeros

Partially observable Markov decision processes (POMDPs) have recently become popular among many AI researchers because they serve as a natural model for planning under uncertainty. Value iteration is a well-known algorithm for finding…

Artificial Intelligence · Computer Science 2011-06-02 N. L. Zhang , W. Zhang

We present a midpoint policy iteration algorithm to solve linear quadratic optimal control problems in both model-based and model-free settings. The algorithm is a variation of Newton's method, and we show that in the model-based setting it…

Optimization and Control · Mathematics 2022-02-16 Benjamin Gravell , Iman Shames , Tyler Summers

We consider the standard optimistic bilevel optimization problem, in particular upper- and lower-level constraints can be coupled. By means of the lower-level value function, the problem is transformed into a single-level optimization…

Optimization and Control · Mathematics 2019-12-17 Andreas Fischer , Alain B. Zemkoho , Shenglong Zhou

Motion planning under uncertainty for an autonomous system can be formulated as a Markov Decision Process with a continuous state space. In this paper, we propose a novel solution to this decision-theoretic planning problem that directly…

Robotics · Computer Science 2020-07-02 Junhong Xu , Kai Yin , Lantao Liu

We consider dynamic programming problems with finite, discrete-time horizons and prohibitively high-dimensional, discrete state-spaces for direct computation of the value function from the Bellman equation. For the case that the value…

Optimization and Control · Mathematics 2020-05-25 Denis Lebedev , Paul Goulart , Kostas Margellos

This paper deals with unconstrained discounted continuous-time Markov decision processes in Borel state and action spaces. Under some conditions imposed on the primitives, allowing unbounded transition rates and unbounded (from both above…

Optimization and Control · Mathematics 2011-03-02 Alexey Piunovskiy , Yi Zhang

In this paper, a convex optimization-based method is proposed for numerically solving dynamic programs in continuous state and action spaces. The key idea is to approximate the output of the Bellman operator at a particular state by the…

Optimization and Control · Mathematics 2020-10-23 Insoon Yang

Recently discovered polyhedral structures of the value function for finite state-action discounted Markov decision processes (MDP) shed light on understanding the success of reinforcement learning. We investigate the value function polytope…

Machine Learning · Computer Science 2022-06-27 Yue Wu , Jesús A. De Loera

In this paper, we propose a novel policy iteration method, called dynamic policy programming (DPP), to estimate the optimal policy in the infinite-horizon Markov decision processes. We prove the finite-iteration and asymptotic l\infty-norm…

Machine Learning · Computer Science 2011-09-09 Mohammad Gheshlaghi Azar , Vicenc Gomez , Hilbert J. Kappen

We consider policy evaluation in infinite-horizon discounted Markov decision problems (MDPs) with infinite spaces. We reformulate this task a compositional stochastic program with a function-valued decision variable that belongs to a…

Optimization and Control · Mathematics 2020-05-19 Alec Koppel , Garrett Warnell , Ethan Stump , Peter Stone , Alejandro Ribeiro

We consider a broad class of dynamic programming (DP) problems that involve a partially linear structure and some positivity properties in their system equation and cost function. We address deterministic and stochastic problems, possibly…

Optimization and Control · Mathematics 2026-04-21 Yuchao Li , Dimitri Bertsekas

Classical value iteration approaches are not applicable to environments with continuous states and actions. For such environments, the states and actions are usually discretized, which leads to an exponential increase in computational…

Machine Learning · Computer Science 2021-05-12 Michael Lutter , Shie Mannor , Jan Peters , Dieter Fox , Animesh Garg

We revisit the finite time analysis of policy gradient methods in the one of the simplest settings: finite state and action MDPs with a policy class consisting of all stochastic policies and with exact gradient evaluations. There has been…

Machine Learning · Computer Science 2021-12-14 Jalaj Bhandari , Daniel Russo