Abstract This paper surveys the field of reinforcement learning from a computer-science
perspective. It is written to be accessible to researchers familiar with machine learning. Both
the historical basis of the field and a broad selection of current work are summarized. ...

In this paper, we bring techniques from operations research to bear on the problem of
choosing optimal actions in partially observable stochastic domains. We begin by
introducing the theory of Markov decision processes (mdps) and partially observable ...

Abstract In the Markov decision process (MDP) formalization of reinforcement learning, a
single adaptive agent interacts with an environment defined by a probabilistic transition
function. In this solipsistic view, secondary agents can only be part of the environment and ...

Abstract The evaluative character of a word is called its semantic orientation. Positive
semantic orientation indicates praise (eg," honest"," intrepid") and negative semantic
orientation indicates criticism (eg," disturbing"," superfluous"). Semantic orientation varies ...

Abstract Activity recognition fits within the bigger framework of context awareness. In this
paper, we report on our efforts to recognize user activity from accelerometer data. Activity
recognition is formulated as a classification problem. Performance of base-level classifiers ...

We have developed a simplified version of the side-pumped pulsed dye laser which has a
spectral halfwidth of 1.25 GHz and a peak power of 10 kW at 600 nm. The basic laser
consists of only four components (output mirror, dye cell, diffraction grating, and tuning ...

Abstract In this paper, we describe the partially observable Markov decision process
(pomdp) approach to nding optimal or near-optimal control strategies for partially observable
stochastic environments, given a complete model of the environment. The pomdp ...

Abstract The authors describe practical methods for calculating the Stark structure of
Rydberg states of the alkali metals based on diagnolization of the energy matrix. A survey of
Stark structures is presented for all of the alkali metals in the vicinity of n= 15. Topics ...

Abstract This paper describes the Q-routing algorithm for packet routing, in which a
reinforcement learning module is embedded into each node of a switching network. Only
local communication is used by each node to keep accurate statistics on which routing ...

A program of research into weakly supervised learning algorithms led us to ask if learning
could occur given only natural selection as feedback. We developed an algorithm that
combined evolution and learning, and tested it in an artificial environment populated with ...