English
Related papers

Related papers: QPLEX Decision Processes: Formulation via Nonlinea…

200 papers

Novel advanced policy gradient (APG) methods, such as Trust Region policy optimization and Proximal policy optimization (PPO), have become the dominant reinforcement learning algorithms because of their ease of implementation and good…

Optimization and Control · Mathematics 2022-03-22 J. G. Dai , Mark Gluzman

This paper focuses on the design of sequential quadratic optimization (commonly known as SQP) methods for solving large-scale nonlinear optimization problems. The most computationally demanding aspect of such an approach is the computation…

Optimization and Control · Mathematics 2020-02-27 James V. Burke , Frank E. Curtis , Hao Wang , Jiashan Wang

We present a method for a certain class of Markov Decision Processes (MDPs) that can relate the optimal policy back to one or more reward sources in the environment. For a given initial state, without fully computing the value function,…

Machine Learning · Computer Science 2018-06-12 Josh Bertram , Peng Wei

We propose a new, nonparametric approach to learning and representing transition dynamics in Markov decision processes (MDPs), which can be combined easily with dynamic programming methods for policy optimisation and value estimation. This…

Machine Learning · Computer Science 2012-06-22 Steffen Grunewalder , Guy Lever , Luca Baldassarre , Massi Pontil , Arthur Gretton

Consumption Markov Decision Processes (CMDPs) are probabilistic decision-making models of resource-constrained systems. In a CMDP, the controller possesses a certain amount of a critical resource, such as electric power. Each action of the…

Formal Languages and Automata Theory · Computer Science 2020-05-18 František Blahoudek , Tomáš Brázdil , Petr Novotný , Melkior Ornik , Pranay Thangeda , Ufuk Topcu

The constrained Markov decision process (CMDP) framework emerges as an important reinforcement learning approach for imposing safety or other critical objectives while maximizing cumulative reward. However, the current understanding of how…

Machine Learning · Computer Science 2024-12-11 Tian Tian , Lin F. Yang , Csaba Szepesvári

Policy gradient methods are widely used in reinforcement learning. Yet, the nonconvexity of policy optimization poses significant challenges in understanding the global convergence of policy gradient methods. For a class of finite-horizon…

Optimization and Control · Mathematics 2026-03-10 Xin Chen , Yifan Hu , Minda Zhao

Load balancing and auto scaling are at the core of scalable, contemporary systems, addressing dynamic resource allocation and service rate adjustments in response to workload changes. This paper introduces a novel model and algorithms for…

Systems and Control · Electrical Eng. & Systems 2024-06-21 S. R. Eshwar , Lucas Lopes Felipe , Alexandre Reiffers-Masson , Daniel Sadoc Menasché , Gugan Thoppe

In this paper, we consider a class of continuous-time, continuous-space stochastic optimal control problems. Building upon recent advances in Markov chain approximation methods and sampling-based algorithms for deterministic path planning,…

Robotics · Computer Science 2012-02-27 Vu Anh Huynh , Sertac Karaman , Emilio Frazzoli

In most common settings of Markov Decision Process (MDP), an agent evaluate a policy based on expectation of (discounted) sum of rewards. However in many applications this criterion might not be suitable from two perspective: first, in risk…

Artificial Intelligence · Computer Science 2017-05-11 Yan Li , Zhaohan Sun

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

Large-scale Markov decision processes (MDPs) require planning algorithms with runtime independent of the number of states of the MDP. We consider the planning problem in MDPs using linear value function approximation with only weak…

Machine Learning · Computer Science 2020-07-14 Roshan Shariff , Csaba Szepesvári

For infinite-horizon average-cost criterion problems, there exist relatively few rigorous approximation and reinforcement learning results. In this paper, for Markov Decision Processes (MDPs) with standard Borel spaces, (i) we first provide…

Optimization and Control · Mathematics 2024-12-10 Ali Devran Kara , Serdar Yuksel

Learning a Markov Decision Process (MDP) from a fixed batch of trajectories is a non-trivial task whose outcome's quality depends on both the amount and the diversity of the sampled regions of the state-action space. Yet, many MDPs are…

Machine Learning · Computer Science 2022-03-08 Giorgio Angelotti , Nicolas Drougard , Caroline P. C. Chanel

Switched linear systems are time-varying nonlinear systems whose dynamics switch between different modes, where each mode corresponds to different linear dynamics. They arise naturally to model unexpected failures, environment uncertainties…

Optimization and Control · Mathematics 2019-04-26 Bo Wu , Murat Cubuktepe , Ufuk Topcu

In this paper, we propose a policy gradient method for confounded partially observable Markov decision processes (POMDPs) with continuous state and observation spaces in the offline setting. We first establish a novel identification result…

Machine Learning · Statistics 2023-12-04 Mao Hong , Zhengling Qi , Yanxun Xu

In this paper, we develop a Topological Approximate Dynamic Programming (TADP) method for planningin stochastic systems modeled as Markov Decision Processesto maximize the probability of satisfying high-level systemspecifications expressed…

Optimization and Control · Mathematics 2020-08-04 Lening Li , Jie Fu

Multi-objective optimization models that encode ordered sequential constraints provide a solution to model various challenging problems including encoding preferences, modeling a curriculum, and enforcing measures of safety. A recently…

Artificial Intelligence · Computer Science 2022-09-16 Kyle Hollins Wray , Stas Tiomkin , Mykel J. Kochenderfer , Pieter Abbeel

A novel reinforcement learning scheme to synthesize policies for continuous-space Markov decision processes (MDPs) is proposed. This scheme enables one to apply model-free, off-the-shelf reinforcement learning algorithms for finite MDPs to…

Systems and Control · Electrical Eng. & Systems 2020-03-03 Abolfazl Lavaei , Fabio Somenzi , Sadegh Soudjani , Ashutosh Trivedi , Majid Zamani

The key assumption underlying linear Markov Decision Processes (MDPs) is that the learner has access to a known feature map $\phi(x, a)$ that maps state-action pairs to $d$-dimensional vectors, and that the rewards and transitions are…

Machine Learning · Computer Science 2023-09-20 Noah Golowich , Ankur Moitra , Dhruv Rohatgi