English
Related papers

Related papers: Planning in entropy-regularized Markov decision pr…

200 papers

Many recent successful (deep) reinforcement learning algorithms make use of regularization, generally based on entropy or Kullback-Leibler divergence. We propose a general theory of regularized Markov Decision Processes that generalizes…

Machine Learning · Computer Science 2019-06-05 Matthieu Geist , Bruno Scherrer , Olivier Pietquin

We propose a general framework for entropy-regularized average-reward reinforcement learning in Markov decision processes (MDPs). Our approach is based on extending the linear-programming formulation of policy optimization in MDPs to…

Machine Learning · Computer Science 2017-05-23 Gergely Neu , Anders Jonsson , Vicenç Gómez

We present a novel $Q$-learning algorithm tailored to solve distributionally robust Markov decision problems where the corresponding ambiguity set of transition probabilities for the underlying Markov decision process is a Wasserstein ball…

Machine Learning · Computer Science 2024-06-21 Ariel Neufeld , Julian Sester

This paper investigates the problem of computing the equilibrium of competitive games, which is often modeled as a constrained saddle-point optimization problem with probability simplex constraints. Despite recent efforts in understanding…

Optimization and Control · Mathematics 2023-01-23 Shicong Cen , Yuting Wei , Yuejie Chi

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

We study the problem of controlling a partially observed Markov decision process (POMDP) to either aid or hinder the estimation of its state trajectory. We encode the estimation objectives via the smoother entropy, which is the conditional…

Systems and Control · Electrical Eng. & Systems 2023-05-10 Timothy L. Molloy , Girish N. Nair

Robust Markov decision processes (MDPs) allow to compute reliable solutions for dynamic decision problems whose evolution is modeled by rewards and partially-known transition probabilities. Unfortunately, accounting for uncertainty in the…

Machine Learning · Computer Science 2020-06-18 Chin Pang Ho , Marek Petrik , Wolfram Wiesemann

In this paper, we consider the problem of controlling a partially observed Markov decision process (POMDP) in order to actively estimate its state trajectory over a fixed horizon with minimal uncertainty. We pose a novel active smoothing…

Systems and Control · Electrical Eng. & Systems 2021-04-06 Timothy L. Molloy , Girish N. Nair

We develop value iteration-based algorithms to solve in a unified manner different classes of combinatorial zero-sum games with mean-payoff type rewards. These algorithms rely on an oracle, evaluating the dynamic programming operator up to…

Computer Science and Game Theory · Computer Science 2024-11-12 Xavier Allamigeon , Stéphane Gaubert , Ricardo D. Katz , Mateusz Skomra

Optimization of expensive computer models with the help of Gaussian process emulators in now commonplace. However, when several (competing) objectives are considered, choosing an appropriate sampling strategy remains an open question. We…

Optimization and Control · Mathematics 2013-10-03 Victor Picheny

Cumulative entropy regularization introduces a regulatory signal to the reinforcement learning (RL) problem that encourages policies with high-entropy actions, which is equivalent to enforcing small deviations from a uniform reference…

Machine Learning · Computer Science 2019-09-16 Felix Leibfried , Jordi Grau-Moya

We study synthesis problems with constraints in partially observable Markov decision processes (POMDPs), where the objective is to compute a strategy for an agent that is guaranteed to satisfy certain safety and performance specifications.…

Strong and weak simulation relations have been proposed for Markov chains, while strong simulation and strong probabilistic simulation relations have been proposed for probabilistic automata. However, decision algorithms for strong and weak…

Logic in Computer Science · Computer Science 2015-07-01 Lijun Zhang , Holger Hermanns , Friedrich Eisenbrand , David N. Jansen

Understanding and analyzing markets is crucial, yet analytical equilibrium solutions remain largely infeasible. Recent breakthroughs in equilibrium computation rely on zeroth-order policy gradient estimation. These approaches commonly…

Computer Science and Game Theory · Computer Science 2023-03-17 Nils Kohring , Fabian R. Pieroth , Martin Bichler

One of the proposed solutions to the equilibrium selection problem for agents learning in repeated games is obtained via the notion of stochastic stability. Learning algorithms are perturbed so that the Markov chain underlying the learning…

Computer Science and Game Theory · Computer Science 2012-07-09 John Wicks , Amy Greenwald

Accurate illness diagnosis is vital for effective treatment and patient safety. Machine learning models are widely used for cancer diagnosis based on historical medical data. However, data imbalance remains a major challenge, leading to…

Machine Learning · Computer Science 2025-03-18 Soufiane Bacha , Huansheng Ning , Belarbi Mostefa , Doreen Sebastian Sarwatt , Sahraoui Dhelim

High sample complexity remains a barrier to the application of reinforcement learning (RL), particularly in multi-agent systems. A large body of work has demonstrated that exploration mechanisms based on the principle of optimism under…

Machine Learning · Computer Science 2021-08-02 Robert Loftin , Aadirupa Saha , Sam Devlin , Katja Hofmann

We present a framework to train a structured prediction model by performing smoothing on the inference algorithm it builds upon. Smoothing overcomes the non-smoothness inherent to the maximum margin structured prediction objective, and…

Machine Learning · Statistics 2019-02-11 Krishna Pillutla , Vincent Roulet , Sham M. Kakade , Zaid Harchaoui

A novel formulation of the clustering problem is introduced in which the task is expressed as an estimation problem, where the object to be estimated is a function which maps a point to its distribution of cluster membership. Unlike…

Machine Learning · Computer Science 2025-10-14 David P. Hofmeyr

This paper studies the finite-time horizon Markov games where the agents' dynamics are decoupled but the rewards can possibly be coupled across agents. The policy class is restricted to local policies where agents make decisions using their…

Computer Science and Game Theory · Computer Science 2023-04-11 Runyu Zhang , Yuyang Zhang , Rohit Konda , Bryce Ferguson , Jason Marden , Na Li