Abstractions for devising compact controllers for MDPs
نویسنده
چکیده
ions for devising compact controllers for MDPs
منابع مشابه
Verification and Refutation of Probabilistic Specifications via Games
We develop an abstraction-based framework to check probabilistic specifications of Markov Decision Processes (MDPs) using the stochastic two-player game abstractions (i.e. “games”) developed by Kwiatkowska et al. as a foundation. We define an abstraction preorder for these game abstractions which enables us to identify many new game abstractions for each MDP — ranging from compact and imprecise...
متن کاملCounterexample-guided Planning
Planning in adversarial and uncertain environments can be modeled as the problem of devising strategies in stochastic perfect information games. These games are generalizations of Markov decision processes (MDPs): there are two (adversarial) players, and a source of randomness. The main practical obstacle to computing winning strategies in such games is the size of the state space. In practice ...
متن کاملPOMDP Homomorphisms
The problem of finding hidden state in a POMDP and the problem of finding abstractions for MDPs are closely related. In this paper, we analyze the connection between existing Predictive State Representation methods [3] and homomorphic reductions of Markov Processes [5, 6]. We formally define a POMDP homomorphism, then extend PSR reduction methods to find POMDP homomorphisms when the original PO...
متن کاملHistory-Based Controller Design and Optimization for Partially Observable MDPs
Partially observable MDPs provide an elegant framework for sequential decision making. Finite-state controllers (FSCs) are often used to represent policies for infinite-horizon problems as they offer a compact representation, simple-toexecute plans, and adjustable tradeoff between computational complexity and policy size. We develop novel connections between optimizing FSCs for POMDPs and the d...
متن کاملWhen Abstractions Met Landmarks
Abstractions and landmarks are two powerful mechanisms for devising admissible heuristics forions and landmarks are two powerful mechanisms for devising admissible heuristics for classical planning. Here we aim at putting them together by integrating landmark information into abstractions, and propose a concrete realization ofions, and propose a concrete realization of this direction suitable f...
متن کاملذخیره در منابع من
با ذخیره ی این منبع در منابع من، دسترسی به آن را برای استفاده های بعدی آسان تر کنید
عنوان ژورنال:
دوره شماره
صفحات -
تاریخ انتشار 2011