Risk forms: representation, disintegration, and application to partially observable two-stage systems
نویسندگان
چکیده
منابع مشابه
Two Solvers of Partially Observable Stochastic Hybrid Systems
We consider the problem of verification of safety specifications for hybrid systems with a controller that has access to partially observations of the state. Two kinds of POMDP Solvers with different goals are studied. First, we get a finite state approximation of the stochastic hybrid system in a uniform grid. Then we can solve the dynamic programs using the existed algorithms. Finally, we pro...
متن کاملProcess-Based Risk Measures for Observable and Partially Observable Discrete-Time Controlled Systems
For controlled discrete-time stochastic processes we introduce a new class of dynamic risk measures, which we call process-based. Their main features are that they measure risk of processes that are functions of the history of the base process. We introduce a new concept of conditional stochastic time consistency and we derive the structure of process-based risk measures enjoying this property....
متن کاملAction representation and partially observable planning using epistemic logic
Planning under incomplete knowledge and partial observability is a tricky issue in AI, because of its computational (temporal and spatial) hardness. Partially observable Markov decision processes (POMDP) are the mainstream approach to partially observable planning. Nevertheless, the applicability of the POMDP approach is limited from the practical side as soon as the set of states has a strong ...
متن کاملRisk-Sensitive Planning in Partially Observable Environments
Partially Observable Markov Decision Process (POMDP) is a popular framework for planning under uncertainty in partially observable domains. Yet, the POMDP model is riskneutral in that it assumes that the agent is maximizing the expected reward of its actions. In contrast, in domains like financial planning, it is often required that the agent decisions are risk-sensitive (maximize the utility o...
متن کاملRisk-sensitive planning in partially observable environments
Partially Observable Markov Decision Process (POMDP) is a popular framework for planning under uncertainty in partially observable domains. Yet, the POMDP model is riskneutral in that it assumes that the agent is maximizing the expected reward of its actions. In contrast, in domains like financial planning, it is often required that the agent decisions are risk-sensitive (maximize the utility o...
متن کاملذخیره در منابع من
با ذخیره ی این منبع در منابع من، دسترسی به آن را برای استفاده های بعدی آسان تر کنید
ژورنال
عنوان ژورنال: Mathematical Programming
سال: 2019
ISSN: 0025-5610,1436-4646
DOI: 10.1007/s10107-019-01376-1