English
Related papers

Related papers: Optimistic Initialization and Greediness Lead to P…

200 papers

Bayesian approaches provide a principled solution to the exploration-exploitation trade-off in Reinforcement Learning. Typical approaches, however, either assume a fully observable environment or scale poorly. This work introduces the…

Artificial Intelligence · Computer Science 2018-11-15 Sammie Katt , Frans Oliehoek , Christopher Amato

We consider the energy minimization problem for undirected graphical models, also known as MAP-inference problem for Markov random fields which is NP-hard in general. We propose a novel polynomial time algorithm to obtain a part of its…

Artificial Intelligence · Computer Science 2015-08-19 Paul Swoboda , Alexander Shekhovtsov , Jörg Hendrik Kappes , Christoph Schnörr , Bogdan Savchynskyy

Learning a near optimal policy in a partially observable system remains an elusive challenge in contemporary reinforcement learning. In this work, we consider episodic reinforcement learning in a reward-mixing Markov decision process (MDP).…

Machine Learning · Computer Science 2022-02-01 Jeongyeol Kwon , Yonathan Efroni , Constantine Caramanis , Shie Mannor

It is well known that for any finite state Markov decision process (MDP) there is a memoryless deterministic policy that maximizes the expected reward. For partially observable Markov decision processes (POMDPs), optimal memoryless policies…

Optimization and Control · Mathematics 2016-02-16 Guido Montufar , Keyan Ghazi-Zahedi , Nihat Ay

Greedy Sampling Methods (GSMs) are widely used to construct approximate solutions of Configuration Optimization Problems (COPs), where a loss functional is minimized over finite configurations of points in a compact domain. While effective…

Optimization and Control · Mathematics 2026-01-09 Evie Nielen , Oliver Tse

This paper presents an initialization method that can approximate a given approximate Ising model with a high degree of accuracy using a factorization machine (FM), a machine learning model. The construction of an Ising models using an FM…

Machine Learning · Computer Science 2025-07-03 Yuya Seki , Hyakka Nakada , Shu Tanaka

Real-world sequential decision making problems commonly involve partial observability, which requires the agent to maintain a memory of history in order to infer the latent states, plan and make good decisions. Coping with partial…

Machine Learning · Computer Science 2022-02-09 Yonathan Efroni , Chi Jin , Akshay Krishnamurthy , Sobhan Miryoosefi

This paper discusses theoretical and experimental aspects of gradient-based approaches to the direct optimization of policy performance in controlled POMDPs. We introduce GPOMDP, a REINFORCE-like algorithm for estimating an approximation to…

Machine Learning · Computer Science 2025-12-08 Jonathan Baxter , Peter L. Bartlett

Partially observable Markov decision processes (POMDPs) is a rich mathematical framework that embraces a large class of complex sequential decision-making problems under uncertainty with limited observations. However, the complexity of…

Systems and Control · Electrical Eng. & Systems 2022-11-29 Mingyu Park , Jaeuk Shin , Insoon Yang

Optimism about the poorly understood states and actions is the main driving force of exploration for many provably-efficient reinforcement learning algorithms. We propose optimism in the face of sensible value functions (OFVF)- a novel…

Machine Learning · Computer Science 2019-04-19 Reazul H. Russel , Tianyi Gu , Marek Petrik

The question of knowing whether the policy Iteration algorithm (PI) for solving Markov Decision Processes (MDPs) has exponential or (strongly) polynomial complexity has attracted much attention in the last 50 years. Recently, Fearnley…

Computer Science and Game Theory · Computer Science 2011-08-19 Romain Hollanders , Jean-Charles Delvenne , Raphaël Jungers

Markov decision processes are widely used for planning and verification in settings that combine controllable or adversarial choices with probabilistic behaviour. The standard analysis algorithm, value iteration, only provides a lower bound…

Logic in Computer Science · Computer Science 2019-10-21 Arnd Hartmanns , Benjamin Lucien Kaminski

Any reinforcement learning algorithm that applies to all Markov decision processes (MDPs) will suffer $\Omega(\sqrt{SAT})$ regret on some MDP, where $T$ is the elapsed time and $S$ and $A$ are the cardinalities of the state and action…

Machine Learning · Statistics 2014-11-04 Ian Osband , Benjamin Van Roy

General-purpose, intelligent, learning agents cycle through sequences of observations, actions, and rewards that are complex, uncertain, unknown, and non-Markovian. On the other hand, reinforcement learning is well-developed for small…

Machine Learning · Computer Science 2009-12-30 Marcus Hutter

We integrate information-theoretic concepts into the design and analysis of optimistic algorithms and Thompson sampling. By making a connection between information-theoretic quantities and confidence bounds, we obtain results that relate…

Machine Learning · Statistics 2019-11-25 Xiuyuan Lu , Benjamin Van Roy

We study reinforcement learning for partially observed Markov decision processes (POMDPs) with infinite observation and state spaces, which remains less investigated theoretically. To this end, we make the first attempt at bridging partial…

Machine Learning · Computer Science 2024-04-02 Qi Cai , Zhuoran Yang , Zhaoran Wang

An automatic program that generates constant profit from the financial market is lucrative for every market practitioner. Recent advance in deep reinforcement learning provides a framework toward end-to-end training of such trading agent.…

Trading and Market Microstructure · Quantitative Finance 2018-07-10 Chien Yi Huang

Designing a deterministic polynomial time algorithm for factoring univariate polynomials over finite fields remains a notorious open problem. In this paper, we present an unconditional deterministic algorithm that takes as input an…

Number Theory · Mathematics 2025-09-17 Daniel Altman

In this work, we study the problem of actively classifying the attributes of dynamical systems characterized as a finite set of Markov decision process (MDP) models. We are interested in finding strategies that actively interact with the…

Systems and Control · Electrical Eng. & Systems 2023-01-06 Bo Wu , Niklas Lauffer , Mohamadreza Ahmadi , Suda Bharadwaj , Zhe Xu , Ufuk Topcu

We introduce a new approximate solution technique for first-order Markov decision processes (FOMDPs). Representing the value function linearly w.r.t. a set of first-order basis functions, we compute suitable weights by casting the…

Artificial Intelligence · Computer Science 2012-07-09 Scott Sanner , Craig Boutilier