Solving Uncertain MDPs with Objectives that are Separable over Instantiations of Model Uncertainty

Solving Uncertain MDPs with Objectives that are Separable over Instantiations of Model Uncertainty

Markov Decision Problems, MDPs offer an effective mechanism for planning under uncertainty. However, due to unavoidable uncertainty over models, it is difficult to obtain an exact specification of an MDP. We are interested in solving MDPs, where transition and reward functions are not exactly specif...

Saved in:

書目詳細資料
Main Authors:	ADULYASAK, Yossiri, VARAKANTHAM, Pradeep, AHMED, Asrar, JAILLET, Patrick
格式:	text
語言:	English
出版:	Institutional Knowledge at Singapore Management University 2015
主題:	Markov Decision Problems (MDPs) Lagrangian Dual Decomposition Bayesian Reinforcement Learning Robust MDPs Artificial Intelligence and Robotics Computer Sciences Numerical Analysis and Scientific Computing
在線閱讀:	https://ink.library.smu.edu.sg/sis_research/2916 https://ink.library.smu.edu.sg/context/sis_research/article/3916/viewcontent/9843_44958_1_PB.pdf
標簽:	添加標簽沒有標簽, 成為第一個標記此記錄!

相似書籍

A STUDY OF MARKOV DECISIONS PROCESSES IN FINITE SPACES AND APPLICATION ON FISHING QUOTAS
由: CECILE MONIQUE HELENE DECKER
出版: (2023)

Reward penalties on augmented states for solving richly constrained RL effectively
由: HAO, Jiang, et al.
出版: (2024)

Dynamic Redeployment to Counter Congestion or Starvation in Vehicle Sharing Systems
由: SUPRIYO GHOSH,, et al.
出版: (2015)

Reliability assessment for distributed systems via communication abstraction and refinement
由: GUI, Lin, et al.
出版: (2015)

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

Online spatio-temporal matching in stochastic and dynamic domains
由: LOWALEKAR, Meghna, et al.
出版: (2018)

Markov decision processes with applications in wireless sensor networks: A survey
由: ALSHEIKH, Abu Mohammad, et al.
出版: (2015)

Regret based Robust Solutions for Uncertain Markov Decision Processes
由: AHMED, Asrar, et al.
出版: (2013)

Short-term liner ship fleet planning with container transshipment and uncertain container shipment demand
由: Meng, Q., et al.
出版: (2014)

Regret-based defense in adversarial reinforcement learning
由: BELAIRE, Roman, et al.
出版: (2024)

Zariski f-decomposition and lagrangian fibration on hyperkähler manifolds
由: Matsushita, D., et al.
出版: (2014)

Solving Selfish Routing Problems with Involuntary Movements and Bounded Rationality
由: VARAKANTHAM, Pradeep Reddy, et al.
出版: (2014)

Dynamic repositioning to reduce lost demand in Bike Sharing Systems
由: GHOSH, Supriyo, et al.
出版: (2017)

Decentralized Stochastic Planning with Anonymity in Interactions
由: VARAKANTHAM, Pradeep, et al.
出版: (2014)

Unleashing Dec-MDPs in Security Games: Enabling Effective Defender Teamwork
由: Shieh, Eric, et al.
出版: (2014)

MDPs as distribution transformers: Affine invariant synthesis for safety objectives
由: AKSHAY, S., et al.
出版: (2023)

Moreau-Yosida regularization of Lagrangian-dual functions for a class of convex optimization problems
由: Meng, F.
出版: (2014)

Approximate Bayesian Computation for Smoothing
由: Martin, J.S., et al.
出版: (2016)

An adaptive sequential Monte Carlo method for approximate Bayesian computation
由: Del Moral, P., et al.
出版: (2016)

An extended study on addressing defender teamwork while accounting for uncertainty in attacker defender games using iterative Dec-MDPs
由: SHIEH, Eric, et al.
出版: (2016)

Efficient Learning for Decomposing and Optimizing Random Networks
由: Li, Haidong, et al.
出版: (2022)

General stochastic user equilibrium traffic assignment problem with link capacity constraints
由: Meng, Q., et al.
出版: (2014)

On the implementation of a log-barrier progressive hedging method for multistage stochastic programs
由: Liu, X., et al.
出版: (2014)

A new decomposition technique in solving multistage stochastic linear programs by infeasible interior point methods
由: Liu, X., et al.
出版: (2013)

Parameter estimation for hidden markov models with intractable likelihoods
由: Dean, T.A., et al.
出版: (2016)

Gradient Free Parameter Estimation for Hidden Markov Models with Intractable Likelihoods
由: Ehrlich, E., et al.
出版: (2016)

Simple re-instantiation of small databases using cloud computing.
由: Tan, T.W., et al.
出版: (2020)

Software failure prediction based on a Markov Bayesian network model
由: Bai, C.G., et al.
出版: (2014)

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

Uncertain Congestion Games with Assorted Human Agent Populations
由: AHMED, Asrar, et al.
出版: (2012)

Decision Support for Assorted Populations in Uncertain and Congested Environments
由: VARAKANTHAM, Pradeep Reddy, et al.
出版: (2013)

Uncertain Congestion Games with Assorted Human Agent Populations
由: VARAKANTHAM, Pradeep Reddy, et al.
出版: (2013)

On methods for solving nonlinear semidefinite optimization problems
由: Sun, J.
出版: (2014)

Mathematical programming formulations for robust airside terminal traffic flow optimisation problem
由: Ng, Kam K.H., et al.
出版: (2022)

Benchmarking of quantum gate decomposition frameworks
由: Verma, Dev
出版: (2025)

Lagrangian-dual functions and Moreau-Yosida regularization
由: Meng, F., et al.
出版: (2013)

Robust service network design problem under uncertain demand
由: Xiang, Xi, et al.
出版: (2023)

Distributionally robust markov decision processes
由: Xu, H., et al.
出版: (2014)

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

Hessian matrix distribution for Bayesian policy gradient reinforcement learning
由: Vien, N.A., et al.
出版: (2013)