Results 1 - 10 of 14,792

Hierarchical Reinforcement Learning with the MAXQ Value Function Decomposition

by Thomas G. Dietterich - Journal of Artificial Intelligence Research , 2000
"... This paper presents a new approach to hierarchical reinforcement learning based on decomposing the target Markov decision process (MDP) into a hierarchy of smaller MDPs and decomposing the value function of the target MDP into an additive combination of the value functions of the smaller MDPs. Th ..."
Abstract - Cited by 443 (6 self) - Add to MetaCart
This paper presents a new approach to hierarchical reinforcement learning based on decomposing the target Markov decision process (MDP) into a hierarchy of smaller MDPs and decomposing the value function of the target MDP into an additive combination of the value functions of the smaller MDPs

The MAXQ Method for Hierarchical Reinforcement Learning

by Thomas G. Dietterich - In Proceedings of the Fifteenth International Conference on Machine Learning , 1998
"... This paper presents a new approach to hierarchical reinforcement learning based on the MAXQ decomposition of the value function. The MAXQ decomposition has both a procedural semantics---as a subroutine hierarchy---and a declarative semantics---as a representation of the value function of a hierarchi ..."
Abstract - Cited by 146 (5 self) - Add to MetaCart
This paper presents a new approach to hierarchical reinforcement learning based on the MAXQ decomposition of the value function. The MAXQ decomposition has both a procedural semantics---as a subroutine hierarchy---and a declarative semantics---as a representation of the value function of a

Hierarchical reinforcement learning

by Magnus Borga , 1993
"... A hierarchical representation of the input-output transition function in a learning system is suggested. The choice of either representing the knowledge in a learning system as a discrete set of input-output pairs or as a continuous input-output transition function is discussed. The conclusion that ..."
Abstract - Cited by 2 (2 self) - Add to MetaCart
that both representations could be e cient, but at di erent levels is made. The di erence between strategies and actions is de ned. An algorithm for using adaptive critic methods in a two-level reinforcement learning system is presented. Two problems that are faced, the hierarchical credit assignment

Hierarchical Reinforcement Learning for Spoken . . .

by Heriberto Cuayáhuitl , 2009
"... This thesis focuses on the problem of scalable optimization of dialogue behaviour in speech-based conversational systems using reinforcement learning. Most previous investigations in dialogue strategy learning have proposed flat reinforcement learning methods, which are more suitable for small-scale ..."
Abstract - Add to MetaCart
-scale spoken dialogue systems. This research formulates the problem in terms of Semi-Markov Decision Processes (SMDPs), and proposes two hierarchical reinforcement learning methods to optimize sub-dialogues rather than full dialogues. The first method uses a hierarchy of SMDPs, where every SMDP ignores

Hierarchical Reinforcement Learning for Spoken . . .

by Heriberto Cuayáhuitl , 2009
"... This thesis focuses on the problem of scalable optimization of dialogue behaviour in speech-based conversational systems using reinforcement learning. Most previous investigations in dialogue strategy learning have proposed flat reinforcement learning methods, which are more suitable for small-scale ..."
Abstract - Add to MetaCart
-scale spoken dialogue systems. This research formulates the problem in terms of Semi-Markov Decision Processes (SMDPs), and proposes two hierarchical reinforcement learning methods to optimize sub-dialogues rather than full dialogues. The first method uses a hierarchy of SMDPs, where every SMDP ignores

Hierarchical Reinforcement Learning

by Magnus Borga Computer, Magnus Borga , 1993
"... A hierarchical representation of the input-output transition function in a learning system is suggested. The choice of either representing the knowledge in a learning system as a discrete set of input-output pairs or as a continuous input-output transition function is discussed. The conclusion that ..."
Abstract - Add to MetaCart
that both representations could be efficient, but at different levels is made. The difference between strategies and actions is defined. An algorithm for using adaptive critic methods in a two-level reinforcement learning system is presented. Two problems that are faced, the hierarchical credit assignment

Bayesian Hierarchical Reinforcement Learning

by Feng Cao, Soumya Ray
"... We describe an approach to incorporating Bayesian priors in the MAXQ framework for hierarchical reinforcement learning (HRL). We define priors on the primitive environment model and on task pseudo-rewards. Since models for composite tasks can be complex, we use a mixed model-based/model-free learnin ..."
Abstract - Cited by 1 (0 self) - Add to MetaCart
We describe an approach to incorporating Bayesian priors in the MAXQ framework for hierarchical reinforcement learning (HRL). We define priors on the primitive environment model and on task pseudo-rewards. Since models for composite tasks can be complex, we use a mixed model

of Hierarchical Reinforcement Learning

by José J. F. Ribas-fern, Alec Solway, Carlos Diuk, Joseph T. Mcguire, Andrew G. Barto, Yael Niv, Matthew M. Botvinick
"... Human behavior displays hierarchical structure: simple actions cohere into subtask sequences, which work together to accomplish overall task goals. Although the neural substrates of such hierarchy have been the target of increasing research, they remain poorly understood. We propose that the computa ..."
Abstract - Add to MetaCart
that the computations supporting hierarchical behavior may relate to those in hierarchical reinforcement learning (HRL), a machine-learning framework that extends reinforcement-learning mechanisms into hierarchical domains. To test this, we leveraged a distinctive prediction arising from HRL. In ordinary reinforcement

Recent advances in hierarchical reinforcement learning

by Andrew G. Barto , 2003
"... A preliminary unedited version of this paper was incorrectly published as part of Volume ..."
Abstract - Cited by 229 (24 self) - Add to MetaCart
A preliminary unedited version of this paper was incorrectly published as part of Volume

Continuous-Time Hierarchical Reinforcement Learning

by Mohammad Ghavamzadeh, Sridhar Mahadevan - In Proceedings of the Eighteenth International Conference on Machine Learning , 2001
"... Hierarchical reinforcement learning (RL) is a general framework which studies how to exploit the structure of actions and tasks to accelerate policy learning in large domains. Prior work in hierarchical RL, such as the MAXQ method, has been limited to the discrete-time discounted reward semiMarkov d ..."
Abstract - Cited by 22 (8 self) - Add to MetaCart
Hierarchical reinforcement learning (RL) is a general framework which studies how to exploit the structure of actions and tasks to accelerate policy learning in large domains. Prior work in hierarchical RL, such as the MAXQ method, has been limited to the discrete-time discounted reward semi
Results 1 - 10 of 14,792