paper-with-me

홈 › Papers

Reinforcement Learning of Risk-Constrained Policies in Markov Decision Processes

2020-02-27 · Tomas Brazdil, Krishnendu Chatterjee, Petr Novotny, Jiri Vahala

Markov decision processes (MDPs) are the defacto frame-work for sequential decision making in the presence ofstochastic uncertainty. A classical optimization criterion forMDPs is to maximize the expected discounted-sum pay-off, which ignores low probability catastrophic events withhighly negative impact on the system. On the other hand,risk-averse policies require the probability of undesirableevents to be below a given threshold, but they do not accountfor optimization of the expected payoff. We consider MDPswith discounted-sum payoff with failure states which repre-sent catastrophic outcomes. The objective of risk-constrainedplanning is to maximize the expected discounted-sum payoffamong risk-averse policies that ensure the probability to en-counter a failure state is below a desired threshold. Our maincontribution is an efficient risk-constrained planning algo-rithm that combines UCT-like search with a predictor learnedthrough interaction with the MDP (in the style of AlphaZero)and with a risk-constrained action selection via linear pro-gramming. We demonstrate the effectiveness of our approachwith experiments on classical MDPs from the literature, in-cluding benchmarks with an order of 10^6 states.

📄 PDF Abstract BibTeX arXiv:2002.12086

Code (1)

snurkabill/MasterThesis 공식 구현 tf

Tasks

Decision Makingreinforcement-learningReinforcement LearningReinforcement Learning (RL)Sequential Decision Making

Similar Papers 제목 키워드 기반

Constrained Risk-Averse Markov Decision Processes

2020-12-04 · Mohamadreza Ahmadi, Ugo Rosolia, Michel D. Ingham, Richard M. Murray 외

We consider the problem of designing policies for Markov decision processes (MDPs) with dynamic coherent risk objectives and constraints. We begin by formulating the problem in a Lagrangian framework. Under the assumptio…

Risk-Constrained Reinforcement Learning with Percentile Risk Criteria

2015-12-05 · Yin-Lam Chow, Mohammad Ghavamzadeh, Lucas Janson, Marco Pavone

In many sequential decision-making problems one is interested in minimizing an expected cumulative cost while taking into account \emph{risk}, i.e., increased awareness of events of small probability and high consequence…

Decision MakingMarketingreinforcement-learningReinforcement Learning+2

Learning Safe Policies with Cost-sensitive Advantage Estimation

2021-01-01 · Bingyi Kang, Shie Mannor, Jiashi Feng

Reinforcement Learning (RL) with safety guarantee is critical for agents performing tasks in risky environments. Recent safe RL algorithms, developed based on Constrained Markov Decision Process (CMDP), mostly take the s…

Reinforcement Learning (RL)

Risk-Averse Decision Making Under Uncertainty

2021-09-09 · Mohamadreza Ahmadi, Ugo Rosolia, Michel D. Ingham, Richard M. Murray 외

A large class of decision making under uncertainty problems can be described via Markov decision processes (MDPs) or partially observable MDPs (POMDPs), with application to artificial intelligence and operations research…

Decision MakingDecision Making Under Uncertainty

UAMDP: Uncertainty-Aware Markov Decision Process for Risk-Constrained Reinforcement Learning from Probabilistic Forecasts

2025-10-09 · Michal Koren, Or Peretz, Tai Dinh, Philip S. Yu arxiv

Sequential decisions in volatile, high-stakes settings require more than maximizing expected return; they require principled uncertainty management. This paper presents the Uncertainty-Aware Markov Decision Process (UAMD…

Reinforcement Learning