• Publications
  • Influence
Planning and Acting in Partially Observable Stochastic Domains
TLDR
In this paper, we bring techniques from operations research to bear on the problem of choosing optimal actions in partially observable stochastic domains. Expand
  • 3,641
  • 425
  • PDF
Reinforcement Learning: A Survey
TLDR
This paper surveys the field of reinforcement learning from a computer-science perspective. Expand
  • 6,723
  • 359
  • PDF
Markov Games as a Framework for Multi-Agent Reinforcement Learning
TLDR
This paper explores the Markov game formalism as a mathematical framework for reasoning about multi-agent environments. Expand
  • 1,937
  • 188
  • PDF
Measuring praise and criticism: Inference of semantic orientation from association
TLDR
We introduce a method for inferring the semantic orientation of a word from its statistical association with a set of positive and negative paradigm words. Expand
  • 1,595
  • 139
  • PDF
Activity Recognition from Accelerometer Data
TLDR
We report on our efforts to recognize user activity from accelerometer data. Expand
  • 1,496
  • 114
  • PDF
Learning Policies for Partially Observable Environments: Scaling Up
TLDR
We show that a combination of two novel approaches performs well on these problems and suggest methods for scaling to even larger and more complicated domains. Expand
  • 700
  • 81
Packet Routing in Dynamically Changing Networks: A Reinforcement Learning Approach
TLDR
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. Expand
  • 710
  • 65
  • PDF
Acting Optimally in Partially Observable Stochastic Domains
TLDR
We describe the partially observable Markov decision process (POMDP) approach to finding optimal or near-optimal control strategies for partially observable stochastic environments, given a complete model of the environment. Expand
  • 680
  • 56
  • PDF
Graphical Models for Game Theory
TLDR
We introduce a compact graph-theoretic representation for multiplayer game theory, and give powerful algorithms for computing their Nash equilibria in certain cases. Expand
  • 640
  • 52
  • PDF
An analysis of model-based Interval Estimation for Markov Decision Processes
TLDR
This paper presents a theoretical analysis of Model-based Interval Estimation and a new variation called MBIE-EB, proving their efficiency even under worst-case conditions. Expand
  • 295
  • 51
  • PDF
...
1
2
3
4
5
...