Results 1  10
of
494,097
Finitetime analysis of the multiarmed bandit problem
 Machine Learning
, 2002
"... Abstract. Reinforcement learning policies face the exploration versus exploitation dilemma, i.e. the search for a balance between exploring the environment to find profitable actions while taking the empirically best action as often as possible. A popular measure of a policy’s success in addressing ..."
Abstract

Cited by 804 (15 self)
 Add to MetaCart
Abstract. Reinforcement learning policies face the exploration versus exploitation dilemma, i.e. the search for a balance between exploring the environment to find profitable actions while taking the empirically best action as often as possible. A popular measure of a policy’s success in addressing
The selfduality equations on a Riemann surface
 Proc. Lond. Math. Soc., III. Ser
, 1987
"... In this paper we shall study a special class of solutions of the selfdual YangMills equations. The original selfduality equations which arose in mathematical physics were defined on Euclidean 4space. The physically relevant solutions were the ones with finite action—the socalled 'instanton ..."
Abstract

Cited by 524 (6 self)
 Add to MetaCart
In this paper we shall study a special class of solutions of the selfdual YangMills equations. The original selfduality equations which arose in mathematical physics were defined on Euclidean 4space. The physically relevant solutions were the ones with finite action—the socalled &apos
Automatic verification of finitestate concurrent systems using temporal logic specifications
 ACM Transactions on Programming Languages and Systems
, 1986
"... We give an efficient procedure for verifying that a finitestate concurrent system meets a specification expressed in a (propositional, branchingtime) temporal logic. Our algorithm has complexity linear in both the size of the specification and the size of the global state graph for the concurrent ..."
Abstract

Cited by 1384 (62 self)
 Add to MetaCart
We give an efficient procedure for verifying that a finitestate concurrent system meets a specification expressed in a (propositional, branchingtime) temporal logic. Our algorithm has complexity linear in both the size of the specification and the size of the global state graph for the concurrent
Coupled hidden Markov models for complex action recognition
, 1996
"... We present algorithms for coupling and training hidden Markov models (HMMs) to model interacting processes, and demonstrate their superiority to conventional HMMs in a vision task classifying twohanded actions. HMMs are perhaps the most successful framework in perceptual computing for modeling and ..."
Abstract

Cited by 497 (22 self)
 Add to MetaCart
We present algorithms for coupling and training hidden Markov models (HMMs) to model interacting processes, and demonstrate their superiority to conventional HMMs in a vision task classifying twohanded actions. HMMs are perhaps the most successful framework in perceptual computing for modeling
Implications of rational inattention
 JOURNAL OF MONETARY ECONOMICS
, 2002
"... A constraint that actions can depend on observations only through a communication channel with finite Shannon capacity is shown to be able to play a role very similar to that of a signal extraction problem or an adjustment cost in standard control problems. The resulting theory looks enough like fa ..."
Abstract

Cited by 514 (10 self)
 Add to MetaCart
A constraint that actions can depend on observations only through a communication channel with finite Shannon capacity is shown to be able to play a role very similar to that of a signal extraction problem or an adjustment cost in standard control problems. The resulting theory looks enough like
Planning and acting in partially observable stochastic domains
 ARTIFICIAL INTELLIGENCE
, 1998
"... 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 mdps (pomdps). We then outline a novel algorithm ..."
Abstract

Cited by 1089 (42 self)
 Add to MetaCart
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 mdps (pomdps). We then outline a novel algorithm
GOLOG: A Logic Programming Language for Dynamic Domains
, 1994
"... This paper proposes a new logic programming language called GOLOG whose interpreter automatically maintains an explicit representation of the dynamic world being modeled, on the basis of user supplied axioms about the preconditions and effects of actions and the initial state of the world. This allo ..."
Abstract

Cited by 621 (72 self)
 Add to MetaCart
This paper proposes a new logic programming language called GOLOG whose interpreter automatically maintains an explicit representation of the dynamic world being modeled, on the basis of user supplied axioms about the preconditions and effects of actions and the initial state of the world
Constrained model predictive control: Stability and optimality
 AUTOMATICA
, 2000
"... Model predictive control is a form of control in which the current control action is obtained by solving, at each sampling instant, a finite horizon openloop optimal control problem, using the current state of the plant as the initial state; the optimization yields an optimal control sequence and t ..."
Abstract

Cited by 696 (15 self)
 Add to MetaCart
Model predictive control is a form of control in which the current control action is obtained by solving, at each sampling instant, a finite horizon openloop optimal control problem, using the current state of the plant as the initial state; the optimization yields an optimal control sequence
Symbolic Model Checking for Realtime Systems
 INFORMATION AND COMPUTATION
, 1992
"... We describe finitestate programs over realnumbered time in a guardedcommand language with realvalued clocks or, equivalently, as finite automata with realvalued clocks. Model checking answers the question which states of a realtime program satisfy a branchingtime specification (given in an ..."
Abstract

Cited by 574 (50 self)
 Add to MetaCart
We describe finitestate programs over realnumbered time in a guardedcommand language with realvalued clocks or, equivalently, as finite automata with realvalued clocks. Model checking answers the question which states of a realtime program satisfy a branchingtime specification (given
Results 1  10
of
494,097