Solving risk-sensitive POMDPs with and without cost observations

Solving risk-sensitive POMDPs with and without cost observations

Partially Observable Markov Decision Processes (POMDPs) are often used to model planning problems under uncertainty. The goal in Risk-Sensitive POMDPs (RS-POMDPs) is to find a policy that maximizes the probability that the cumulative cost is within some user-defined cost threshold. In this paper, un...

Saved in:

書目詳細資料
Main Authors:	HOU, Ping, YEOH, William, Pradeep VARAKANTHAM
格式:	text
語言:	English
出版:	Institutional Knowledge at Singapore Management University 2016
主題:	Theory and Algorithms
在線閱讀:	https://ink.library.smu.edu.sg/sis_research/3605 https://ink.library.smu.edu.sg/context/sis_research/article/4606/viewcontent/RSPOMDP.pdf
標簽:	添加標簽沒有標簽, 成為第一個標記此記錄!
機構:	Singapore Management University
語言:	English

相似書籍

Prioritized Shaping of Models for Solving DEC-POMDPs
由: VARAKANTHAM, Pradeep Reddy, et al.
出版: (2012)

Adaptive decision support for structured organizations: A case for OrgPOMDPs
由: VARAKANTHAM, Pradeep Reddy, et al.
出版: (2011)

Implementation Techniques for Solving POMDPs in Personal Assistant Domains
由: VARAKANTHAM, Pradeep Reddy, et al.
出版: (2006)

Offline RL with discrete proxy representations for generalizability in POMDPs
由: GU, Pengjie, et al.
出版: (2023)

Revisiting Risk-Sensitive MDPs: New Algorithms and Results
由: HOU, Ping, et al.
出版: (2014)

Detecting communities using coordination games: A short paper
由: ARAVA, Radhika, et al.
出版: (2016)

Networked Distributed POMDPs: A Synthesis of Distributed Constraint Optimization and POMDPs
由: NAIR, Ranjit, et al.
出版: (2005)

Exploiting anonymity and homogeneity in factored Dec-MDPs through pre-computed binomial distributions
由: RANJAN KUMAR, Rajiv, et al.
出版: (2017)

Risk-Sensitive Planning in Partially Observable
由: MARECKI, Janusz, et al.
出版: (2010)

Correlated learning for aggregation systems
由: VERMA, Tanvi, et al.
出版: (2019)

Exploiting Belief Bounds: Practical POMDPs for Personal Assistant Agents
由: VARAKANTHAM, Pradeep, et al.
出版: (2005)

Scalable greedy algorithms for task/resource constrained multi-agent stochastic planning
由: AGRAWAL, Pritee, et al.
出版: (2016)

Robust Partial Order Schedules for RCPSP/max with Durational Uncertainty
由: FU, Na, et al.
出版: (2016)

RMIX: Learning risk-sensitive policies for cooperative reinforcement learning agents
由: QIU, Wei, et al.
出版: (2021)

Generic conversions from CPA to CCA without ciphertext expansion for threshold ABE with constant-size ciphertexts
由: LAI, J, et al.
出版: (2022)

Online contextual influence maximization with costly observations
由: SARITAC, Omer, et al.
出版: (2019)

Microblog search and filtering with time sensitive feedback and thresholding based on BM25
由: GAO, Wei, et al.
出版: (2012)

Distributed Model Shaping for Scaling to Decentralized POMDPs with hundreds of agents
由: VELAGAPUDI, Prasanna, et al.
出版: (2011)

Imitate the good and avoid the bad: An incremental approach to safe reinforcement learning
由: HOANG, Minh Huy, et al.
出版: (2024)

Introducing Communication in Dis-POMDPs with Locality of Interaction
由: TASAKI, Makoto, et al.
出版: (2010)

Winning back the CUP for Distributed POMDPs: Planning over continuous belief spaces
由: VARAKANTHAM, Pradeep, et al.
出版: (2006)

Solving fractional differential equations on a quantum computer: A variational approach
由: LEONG, Fong Yew, et al.
出版: (2024)

Sampling based approaches for minimizing regret in uncertain Markov Decision Problems (MDPs)
由: AHMED, Asrar, et al.
出版: (2017)

Not All Agents are Equal: Scaling up Distributed POMDPs for Agent Networks
由: MARECKI, Janusz, et al.
出版: (2008)

Letting loose a SPIDER on a network of POMDPs: Generating quality guranteed policies
由: VARAKANTHAM, Pradeep Reddy, et al.
出版: (2007)

Exploring tweets normalization and query time sensitivity for Twitter search
由: WEI, Zhongyu, et al.
出版: (2011)

Automated Generation of Interaction Graphs for Value-Factored Decentralized POMDPs
由: YEOH, William, et al.
出版: (2013)

Risk-sensitive stochastic orienteering problems for trip optimization in urban environments
由: VARAKANTHAM, Pradeep, et al.
出版: (2018)

Towards Efficient Computation of Quality Bounded Solutions in POMDPs: Expected Value Approximation and Dynamic Disjunctive Beliefs
由: VARAKANTHAM, Pradeep Reddy, et al.
出版: (2007)

Lagrangian Relaxation for Large-Scale Multi-Agent Planning
由: Gordon, Geoffrey J., et al.
出版: (2012)

Incremental DCOP Search Algorithms for Solving Dynamic DCOP Problems
由: YEOH, William, et al.
出版: (2011)

Incremental DCOP Search Algorithms for Solving Dynamic DCOP Problems
由: YEOH, William, et al.
出版: (2015)

A simple polynomial-time randomized distributed algorithm for connected row convex constraints
由: KUMAR, T. K. Satish, et al.
出版: (2014)

Solving the teacher assignment-course scheduling problem by a hybrid Algorithm
由: GUNAWAN, Aldy, et al.
出版: (2007)

Empirical risk landscape analysis for understanding deep neural networks
由: ZHOU, Pan, et al.
出版: (2018)

A review on swarm intelligence and evolutionary algorithms for solving flexible job shop scheduling problems
由: GAO, Kaizhou, et al.
出版: (2019)

PRESS: Personalized event scheduling recommender system (demonstration)
由: LAU, Hoong Chuin, et al.
出版: (2016)

Herbal medicines in functional dyspepsia—Untapped opportunities not without risks
由: Gwee, Kok-Ann, et al.
出版: (2022)

Novel approach to solving stochastic constrained shortest path problem with quantum computing
由: Yang, Richard Chen Xiao
出版: (2023)

Optimizing expectation with guarantees in POMDPs
由: CHATTERJEE, Krishnendu, et al.
出版: (2017)