English
Related papers

Related papers: How to Explore with Belief: State Entropy Maximiza…

200 papers

The problem of pure exploration in Markov decision processes has been cast as maximizing the entropy over the state distribution induced by the agent's policy, an objective that has been extensively studied. However, little attention has…

Machine Learning · Computer Science 2024-06-19 Riccardo Zamboni , Duilio Cirino , Marcello Restelli , Mirco Mutti

We study the problem of synthesizing a controller that maximizes the entropy of a partially observable Markov decision process (POMDP) subject to a constraint on the expected total reward. Such a controller minimizes the predictability of…

Optimization and Control · Mathematics 2021-05-18 Yagiz Savas , Michael Hibbard , Bo Wu , Takashi Tanaka , Ufuk Topcu

Reinforcement learning in partially observable environments is typically challenging, as it requires agents to learn an estimate of the underlying system state. These challenges are exacerbated in multi-agent settings, where agents learn…

Artificial Intelligence · Computer Science 2025-04-14 Paul J. Pritz , Kin K. Leung

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

The traditional approach to POMDPs is to convert them into fully observed MDPs by considering a belief state as an information state. However, a belief-state based approach requires perfect knowledge of the system dynamics and is therefore…

Systems and Control · Electrical Eng. & Systems 2024-10-01 Amit Sinha , Aditya Mahajan

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

Maximum entropy reinforcement learning motivates agents to explore states and actions to maximize the entropy of some distribution, typically by providing additional intrinsic rewards proportional to that entropy function. In this paper, we…

Machine Learning · Computer Science 2026-03-20 Adrien Bolland , Gaspard Lambrechts , Damien Ernst

Maximum entropy reinforcement learning integrates exploration into policy learning by providing additional intrinsic rewards proportional to the entropy of some distribution. In this paper, we propose a novel approach in which the intrinsic…

Machine Learning · Computer Science 2025-09-30 Adrien Bolland , Gaspard Lambrechts , Damien Ernst

Policy-gradient methods have received increased attention recently as a mechanism for learning to act in partially observable environments. They have shown promise for problems admitting memoryless policies but have been less successful…

Machine Learning · Computer Science 2025-12-08 Douglas Aberdeen , Jonathan Baxter

The principle of maximum entropy is a broadly applicable technique for computing a distribution with the least amount of information possible while constrained to match empirically estimated feature expectations. However, in many real-world…

Machine Learning · Computer Science 2022-08-16 Kenneth Bogert , Yikang Gui , Prashant Doshi

In the maximum state entropy exploration framework, an agent interacts with a reward-free environment to learn a policy that maximizes the entropy of the expected state visitations it is inducing. Hazan et al. (2019) noted that the class of…

Machine Learning · Computer Science 2022-07-11 Mirco Mutti , Riccardo De Santi , Marcello Restelli

We consider a Reinforcement Learning setup where an agent interacts with an environment in observation-reward-action cycles without any (esp.\ MDP) assumptions on the environment. State aggregation and more generally feature reinforcement…

Artificial Intelligence · Computer Science 2014-07-15 Marcus Hutter

The agent learns to organize decision behavior to achieve a behavioral goal, such as reward maximization, and reinforcement learning is often used for this optimization. Learning an optimal behavioral strategy is difficult under the…

Machine Learning · Computer Science 2023-05-09 Kazuki Takahashi , Tomoki Fukai , Yutaka Sakai , Takashi Takekawa

Partially observable Markov decision processes (POMDPs) are a general framework for sequential decision-making under latent state uncertainty, yet learning in POMDPs is intractable in the worst case. Motivated by sensing and probing…

Machine Learning · Computer Science 2026-01-27 Ming Shi , Yingbin Liang , Ness B. Shroff

I formulate an entropy-rate maximization problem at the observable level for stochastic processes observed through an information-reducing observation map. For a visible stationary law, the map determines an observational fiber of hidden…

Information Theory · Computer Science 2026-04-14 Oleg Kiriukhin

We study an approximation method for partially observed Markov decision processes (POMDPs) with continuous spaces. Belief MDP reduction, which has been the standard approach to study POMDPs requires rigorous approximation methods for…

Optimization and Control · Mathematics 2025-01-20 Ali Devran Kara , Erhan Bayraktar , Serdar Yuksel

Partially Observable Markov Decision Processes (POMDPs) are used to model environments where the full state cannot be perceived by an agent. As such the agent needs to reason taking into account the past observations and actions. However,…

Machine Learning · Computer Science 2023-10-27 Raphael Avalos , Florent Delgrange , Ann Nowé , Guillermo A. Pérez , Diederik M. Roijers

In most real-world reinforcement learning applications, state information is only partially observable, which breaks the Markov decision process assumption and leads to inferior performance for algorithms that conflate observations with…

Machine Learning · Computer Science 2024-06-12 Hongming Zhang , Tongzheng Ren , Chenjun Xiao , Dale Schuurmans , Bo Dai

Entropy regularization is commonly used to improve policy optimization in reinforcement learning. It is believed to help with \emph{exploration} by encouraging the selection of more stochastic policies. In this work, we analyze this claim…

Machine Learning · Computer Science 2019-06-11 Zafarali Ahmed , Nicolas Le Roux , Mohammad Norouzi , Dale Schuurmans

We study the problem of synthesizing a controller that maximizes the entropy of a partially observable Markov decision process (POMDP) subject to a constraint on the expected total reward. Such a controller minimizes the predictability of a…

Optimization and Control · Mathematics 2019-09-16 Michael Hibbard , Yagiz Savas , Bo Wu , Takashi Tanaka , Ufuk Topcu
‹ Prev 1 2 3 10 Next ›