Reinforcement Learning in Robust Markov Decision Processes
نویسندگان
چکیده
An important challenge in Markov decision processes is to ensure robustness with respect to unexpected or adversarial system behavior while taking advantage of well-behaving parts of the system. We consider a problem setting where some unknown parts of the state space can have arbitrary transitions while other parts are purely stochastic. We devise an algorithm that is adaptive to potentially adversarial behavior and show that it achieves similar regret bounds as the purely stochastic case.
منابع مشابه
Utilizing Generalized Learning Automata for Finding Optimal Policies in MMDPs
Multi agent Markov decision processes (MMDPs), as the generalization of Markov decision processes to the multi agent case, have long been used for modeling multi agent system and are used as a suitable framework for Multi agent Reinforcement Learning. In this paper, a generalized learning automata based algorithm for finding optimal policies in MMDP is proposed. In the proposed algorithm, MMDP ...
متن کاملGaussian Processes for Fast Policy Optimisation of POMDP-based Dialogue Managers
Modelling dialogue as a Partially Observable Markov Decision Process (POMDP) enables a dialogue policy robust to speech understanding errors to be learnt. However, a major challenge in POMDP policy learning is to maintain tractability, so the use of approximation is inevitable. We propose applying Gaussian Processes in Reinforcement learning of optimal POMDP dialogue policies, in order (1) to m...
متن کاملLogical Markov Decision Programs
Motivated by the interest in relational reinforcement learning, we introduce a novel representation formalism, called logical Markov decision programs (LOMDPs), that integrates Markov Decision Processes with Logic Programs. Using LOMDPs one can compactly and declaratively represent complex relational Markov decision processes. Within this framework we then develop a theory of reinforcement lear...
متن کاملAn Analysis of Direct Reinforcement Learning in Non-Markovian Domains
It is well known that for Markov decision processes, the policies stable under policy iteration and the standard reinforcement learning methods are exactly the optimal policies. In this paper, we investigate the conditions for policy stability in the more general situation when the Markov property cannot be assumed. We show that for a general class of non-Markov decision processes, if actual re...
متن کاملAutomated Discovery of Options in Factored Reinforcement Learning
Factored Reinforcement Learning (FRL) is a method to solve Factored Markov Decision Processes when the structure of the transition and reward functions of the problem must be learned. In this paper, we present TeXDYNA, an algorithm that combines the abstraction techniques of Semi-Markov Decision Processes to perform the automatic hierarchical decomposition of the problem with an FRL method. The...
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 2013