English
Related papers

Related papers: From Relative Entropy to Minimax: A Unified Framew…

200 papers

In this paper, we consider a Markov decision process (MDP) with a Borel state space $\textbf{X}\cup\{\Delta\}$, where $\Delta$ is an absorbing state (cemetery), and a Borel action space $\textbf{A}$. We consider the space of finite…

Optimization and Control · Mathematics 2023-07-07 Alexey Piunovskiy , Yi Zhang

The policy gradient theorem is defined based on an objective with respect to the initial distribution over states. In the discounted case, this results in policies that are optimal for one distribution over initial states, but may not be…

Machine Learning · Computer Science 2019-12-12 Riashat Islam , Raihan Seraj , Pierre-Luc Bacon , Doina Precup

Count-based exploration algorithms are known to perform near-optimally when used in conjunction with tabular reinforcement learning (RL) methods for solving small discrete Markov decision processes (MDPs). It is generally thought that…

Artificial Intelligence · Computer Science 2017-12-06 Haoran Tang , Rein Houthooft , Davis Foote , Adam Stooke , Xi Chen , Yan Duan , John Schulman , Filip De Turck , Pieter Abbeel

We study risk-sensitive Reinforcement Learning (RL), where we aim to maximize the Conditional Value at Risk (CVaR) with a fixed risk tolerance $\tau$. Prior theoretical work studying risk-sensitive RL focuses on the tabular Markov Decision…

Machine Learning · Computer Science 2023-11-21 Yulai Zhao , Wenhao Zhan , Xiaoyan Hu , Ho-fung Leung , Farzan Farnia , Wen Sun , Jason D. Lee

In this work, we prove that, in linear MDPs, the feature dimension $d$ is lower bounded by $S/U$ in order to aptly represent transition probabilities, where $S$ is the size of the state space and $U$ is the maximum size of directly…

Machine Learning · Statistics 2024-11-01 Joongkyu Lee , Min-hwan Oh

In a reward-free environment, what is a suitable intrinsic objective for an agent to pursue so that it can learn an optimal task-agnostic exploration policy? In this paper, we argue that the entropy of the state distribution induced by…

Machine Learning · Computer Science 2021-03-02 Mirco Mutti , Lorenzo Pratissoli , Marcello Restelli

Motivated by the recent discovery of a statistical and computational reduction from contextual bandits to offline regression (Simchi-Levi and Xu, 2021), we address the general (stochastic) Contextual Markov Decision Process (CMDP) problem…

Machine Learning · Computer Science 2024-05-29 Jian Qian , Haichen Hu , David Simchi-Levi

An optimal feedback controller for a given Markov decision process (MDP) can in principle be synthesized by value or policy iteration. However, if the system dynamics and the reward function are unknown, a learning agent must discover an…

Machine Learning · Computer Science 2019-07-19 Boris Belousov , Jan Peters

This paper studies convergence properties of optimal values and actions for discounted and average-cost Markov Decision Processes (MDPs) with weakly continuous transition probabilities and applies these properties to the stochastic…

Optimization and Control · Mathematics 2017-03-21 Eugene A. Feinberg , Mark E. Lewis

We present a method for solving implicit (factored) Markov decision processes (MDPs) with very large state spaces. We introduce a property of state space partitions which we call epsilon-homogeneity. Intuitively, an epsilon-homogeneous…

Artificial Intelligence · Computer Science 2013-02-08 Thomas L. Dean , Robert Givan , Sonia Leach

Constrained decision-making is essential for designing safe policies in real-world control systems, yet simulated environments often fail to capture real-world adversities. We consider the problem of learning a policy that will maximize the…

Machine Learning · Computer Science 2026-02-10 Sourav Ganguly , Kishan Panaganti , Arnob Ghosh , Adam Wierman

We study a class of sequential decision-making problems with augmented predictions, potentially provided by a machine learning algorithm. In this setting, the decision-maker receives prediction intervals for unknown parameters that become…

Machine Learning · Computer Science 2025-05-05 Xin Chen , Yuze Chen , Yuan Zhou

A promising technique for exploration is to maximize the entropy of visited state distribution, i.e., state entropy, by encouraging uniform coverage of visited state space. While it has been effective for an unsupervised setup, it tends to…

Machine Learning · Computer Science 2024-08-12 Dongyoung Kim , Jinwoo Shin , Pieter Abbeel , Younggyo Seo

Self-supervised goal proposal and reaching is a key component for exploration and efficient policy learning algorithms. Such a self-supervised approach without access to any oracle goal sampling distribution requires deep exploration and…

Robotics · Computer Science 2021-04-28 Homanga Bharadhwaj , Animesh Garg , Florian Shkurti

We propose a finite-state, decentralized decision and control framework for multi-agent ground coverage. The approach decomposes the problem into two coupled components: (i) the structural design of a deep neural network (DNN) induced by…

Systems and Control · Electrical Eng. & Systems 2026-01-06 Hossein Rastgoftar

In many real-world decision problems there is partially observed, hidden or latent information that remains fixed throughout an interaction. Such decision problems can be modeled as Latent Markov Decision Processes (LMDPs), where a latent…

Machine Learning · Computer Science 2024-06-27 Jeongyeol Kwon , Shie Mannor , Constantine Caramanis , Yonathan Efroni

We study Markov Decision Processes (MDP) wherein states correspond to causal graphs that stochastically generate rewards. In this setup, the learner's goal is to identify atomic interventions that lead to high rewards by intervening on…

Machine Learning · Computer Science 2021-11-02 Rahul Madhavan , Aurghya Maiti , Gaurav Sinha , Siddharth Barman

The standard Markov Decision Process (MDP) formulation hinges on the assumption that an action is executed immediately after it was chosen. However, assuming it is often unrealistic and can lead to catastrophic failures in applications such…

Machine Learning · Computer Science 2023-12-14 Esther Derman , Gal Dalal , Shie Mannor

We consider a hidden Markov model with multiple observation processes, one of which is chosen at each point in time by a policy---a deterministic function of the information state---and attempt to determine which policy minimises the…

Probability · Mathematics 2015-03-17 James Y. Zhao

We consider deterministic Markov decision processes (MDPs) and apply max-plus algebra tools to approximate the value iteration algorithm by a smaller-dimensional iteration based on a representation on dictionaries of value functions. The…

Machine Learning · Computer Science 2019-06-21 Francis Bach