English
Related papers

Related papers: Critic Algorithms using Cooperative Networks

200 papers

This paper studies the policy mirror descent (PMD) method, which is a general policy optimization framework in reinforcement learning and can cover a wide range of policy gradient methods by specifying difference mirror maps. Existing…

Optimization and Control · Mathematics 2026-01-01 Wenye Li , Hongxu Chen , Jiacai Liu , Ke Wei

We develop a method for computing policies in Markov decision processes with risk-sensitive measures subject to temporal logic constraints. Specifically, we use a particular risk-sensitive measure from cumulative prospect theory, which has…

Artificial Intelligence · Computer Science 2020-04-21 Murat Cubuktepe , Ufuk Topcu

Most reinforcement learning methods are based upon the key assumption that the transition dynamics and reward functions are fixed, that is, the underlying Markov decision process is stationary. However, in many real-world applications, this…

Machine Learning · Computer Science 2020-09-23 Yash Chandak , Georgios Theocharous , Shiv Shankar , Martha White , Sridhar Mahadevan , Philip S. Thomas

The Distributed Diffusion Kalman Filter (DDKF) algorithm in all its magnitude has earned great attention lately and has shown an elaborate way to address the issue of distributed optimization over networks. Estimation and tracking of a…

We study continuous action reinforcement learning problems in which it is crucial that the agent interacts with the environment only through safe policies, i.e.,~policies that do not take the agent to undesirable situations. We formulate…

Machine Learning · Computer Science 2019-02-13 Yinlam Chow , Ofir Nachum , Aleksandra Faust , Edgar Duenez-Guzman , Mohammad Ghavamzadeh

Policy gradient methods in reinforcement learning update policy parameters by taking steps in the direction of an estimated gradient of policy value. In this paper, we consider the statistically efficient estimation of policy gradients from…

Machine Learning · Statistics 2020-02-21 Nathan Kallus , Masatoshi Uehara

We study a primal-dual (PD) reinforcement learning (RL) algorithm for online constrained Markov decision processes (CMDPs). Despite its widespread practical use, the existing theoretical literature on PD-RL algorithms for this problem only…

Reinforcement learning, mathematically described by Markov Decision Problems, may be approached either through dynamic programming or policy search. Actor-critic algorithms combine the merits of both approaches by alternating between steps…

Machine Learning · Computer Science 2023-01-31 Harshat Kumar , Alec Koppel , Alejandro Ribeiro

Automatic differentiation (AD) has driven recent advances in machine learning, including deep neural networks and Hamiltonian Markov Chain Monte Carlo methods. Partially observed nonlinear stochastic dynamical systems have proved resistant…

Methodology · Statistics 2024-07-04 Kevin Tan , Giles Hooker , Edward L. Ionides

Markov decision processes (MDPs) is viewed as an optimization of an objective function over certain linear operators over general function spaces. A new existence result is established for the existence of optimal policies in general MDPs,…

Machine Learning · Computer Science 2026-04-01 Abhishek Gupta , Aditya Mahajan

There is significant recent interest to parallelize deep learning algorithms in order to handle the enormous growth in data and model sizes. While most advances focus on model parallelization and engaging multiple computing agents via using…

Machine Learning · Statistics 2017-06-27 Zhanhong Jiang , Aditya Balu , Chinmay Hegde , Soumik Sarkar

We present differentiable predictive control (DPC), a method for learning constrained neural control policies for linear systems with probabilistic performance guarantees. We employ automatic differentiation to obtain direct policy…

Systems and Control · Electrical Eng. & Systems 2022-01-28 Jan Drgona , Aaron Tuor , Draguna Vrabie

Power systems that need to integrate renewables at a large scale must account for the high levels of uncertainty introduced by these power sources. This can be accomplished with a system of many distributed grid-level storage devices.…

Optimization and Control · Mathematics 2020-02-04 Joseph L. Durante , Juliana Nascimento , Warren B. Powell

In this paper, we propose a novel reduced-rank adaptive filtering algorithm by blending the idea of the Krylov subspace methods with the set-theoretic adaptive filtering framework. Unlike the existing Krylov-subspace-based reduced-rank…

Information Theory · Computer Science 2013-06-28 R. C. de Lamare , M. Yukawa , I. Yamada

This paper is concerned with developing a novel distributed Kalman filtering algorithm over wireless sensor networks based on randomized consensus strategy. Compared with the centralized algorithm, distributed filtering techniques require…

Systems and Control · Computer Science 2018-10-08 Jiahu Qin , Jie Wang , Ling Shi , Yu Kang

Finding optimal policies which maximize long term rewards of Markov Decision Processes requires the use of dynamic programming and backward induction to solve the Bellman optimality equation. However, many real-world problems require…

Machine Learning · Computer Science 2023-01-10 Mridul Agarwal , Vaneet Aggarwal

The Markov Blanket Bayesian Classifier is a recently-proposed algorithm for construction of probabilistic classifiers. This paper presents an empirical comparison of the MBBC algorithm with three other Bayesian classifiers: Naive Bayes,…

Machine Learning · Computer Science 2007-05-23 Michael G. Madden

In this paper, we investigate learning temporal abstractions in cooperative multi-agent systems, using the options framework (Sutton et al, 1999). First, we address the planning problem for the decentralized POMDP represented by the…

Artificial Intelligence · Computer Science 2020-03-23 Jhelum Chakravorty , Nadeem Ward , Julien Roy , Maxime Chevalier-Boisvert , Sumana Basu , Andrei Lupu , Doina Precup

Filtering---estimating the state of a partially observable Markov process from a sequence of observations---is one of the most widely studied problems in control theory, AI, and computational statistics. Exact computation of the posterior…

Artificial Intelligence · Computer Science 2013-01-07 Bhaskara Marthi , Hanna Pasula , Stuart Russell , Yuval Peres

In the paper, we design a novel Bregman gradient policy optimization framework for reinforcement learning based on Bregman divergences and momentum techniques. Specifically, we propose a Bregman gradient policy optimization (BGPO) algorithm…

Machine Learning · Computer Science 2022-03-17 Feihu Huang , Shangqian Gao , Heng Huang