This paper presents a simple method for exact online inference and approximate decision making, applicable to large or partially observable Markov decision processes. The approach is based on a closed form Bayesian inference procedure for a class of context models which con-tains variable order Markov decision processes. The models can be used for prediction, and thus for decision theoretic planning. The other novel step of this paper is to use the belief (context distribution) at any given time as a compact representation of system state, in a manner similar to predictive state representations. Since the belief update is linear time in the worst case, this allows for computationally efficient value iteration and reactive learning algorithm...
We develop a new Bayesian modelling framework for the class of higher-order, variable-memory Markov ...
This thesis is about chance and choice, or decisions under uncertainty. The desire for creating an ...
For many applications of Markov Decision Processes (MDPs), the transition function cannot be specifi...
Abstract—This paper presents the Bayesian Optimistic Plan-ning (BOP) algorithm, a novel model-based ...
This dissertation discusses the mathematical modeling of dynamical systems under uncertainty, Bayesi...
context-based model Markov models have been a keystone in Artificial Intelligence for many decades. ...
In this chapter, we introduce the notion of simple context-free decision processes, which are an ext...
<p>This dissertation describes sequential decision making problems in non-stationary environments. O...
Markov Decision Processes (MDPs) are a mathematical framework for modeling sequential decision probl...
Markov Decision Processes (MDPs) are not able to make use of domain information effectively due to t...
: Partially-observable Markov decision processes provide a very general model for decision-theoretic...
We present a simple, effective generalisation of variable order Markov models to full on-line Bayesi...
Partially observable Markov decision processes (POMDPs) provide a principled approach to planning u...
Inference in Markov Decision Processes has recently received interest as a means to infer goals of...
Multiple-environment Markov decision processes (MEMDPs) are MDPs equipped with not one, but multiple...
We develop a new Bayesian modelling framework for the class of higher-order, variable-memory Markov ...
This thesis is about chance and choice, or decisions under uncertainty. The desire for creating an ...
For many applications of Markov Decision Processes (MDPs), the transition function cannot be specifi...
Abstract—This paper presents the Bayesian Optimistic Plan-ning (BOP) algorithm, a novel model-based ...
This dissertation discusses the mathematical modeling of dynamical systems under uncertainty, Bayesi...
context-based model Markov models have been a keystone in Artificial Intelligence for many decades. ...
In this chapter, we introduce the notion of simple context-free decision processes, which are an ext...
<p>This dissertation describes sequential decision making problems in non-stationary environments. O...
Markov Decision Processes (MDPs) are a mathematical framework for modeling sequential decision probl...
Markov Decision Processes (MDPs) are not able to make use of domain information effectively due to t...
: Partially-observable Markov decision processes provide a very general model for decision-theoretic...
We present a simple, effective generalisation of variable order Markov models to full on-line Bayesi...
Partially observable Markov decision processes (POMDPs) provide a principled approach to planning u...
Inference in Markov Decision Processes has recently received interest as a means to infer goals of...
Multiple-environment Markov decision processes (MEMDPs) are MDPs equipped with not one, but multiple...
We develop a new Bayesian modelling framework for the class of higher-order, variable-memory Markov ...
This thesis is about chance and choice, or decisions under uncertainty. The desire for creating an ...
For many applications of Markov Decision Processes (MDPs), the transition function cannot be specifi...