# the maxq method for hierarchical reinforcement learning

Hierarchical reinforcement learning with the MAXQ value function… » This paper presents a new approach to hierarchical reinforcement learning based on decomposing the target Markov decision process (MDP) into a hierarchy of ... Dl.acm.org

The MAXQ Method for Hierarchical Reinforcement Learning Thomas… » The MAXQ Method for Hierarchical Reinforcement Learning. Thomas G. Dietterich. Department of Computer Science. Oregon State University. Corvallis, Oregon ... Web.engr.oregonstate.edu

Hierarchical Reinforcement Learning with the MAXQ Value Function… » This paper presents a new approach to hierarchical reinforcement learning based… method. This paper defines the MAXQ hierarchy, proves formal results on its ... Jair.org

A New Learning Algorithm for the Maxq Hierarchical Reinforcement… » Abstract: The MAXQ hierarchical reinforcement learning method is computationally expensive in applications with deep hierarchy. In this paper, we propose a ... Ieeexplore.ieee.org

[cs/9905014] Hierarchical Reinforcement Learning with the MAXQ… » May 21, 1999… Computer Science > Machine Learning… Abstract: This paper presents the MAXQ approach to hierarchical reinforcement learning based on ... Arxiv.org

An Overview of MAXQ Hierarchical Reinforcement Learning » But this approach does not scale to tasks such as robot soccer or air traffic control that have a complex, hierarchical structure. If reinforcement learning is to scale. Link.springer.com

The MAXQ Method for Hierarchical Reinforcement Learning » MAXQ unifies and extends previous work on hierarchical reinforcement learning by Singh, Kaelbling, and Dayan and Hinton. Conditions under which the MAXQ ... Citeseerx.ist.psu.edu

Hierarchical Reinforcement Learning with the MAXQ Value Function… » This paper presents a new approach to hierarchical reinforcement learning based… method. This paper de nes the MAXQ hierarchy, proves formal results on its ... Cs.cmu.edu

The MAXQ Method for Hierarchical Reinforcement Learning » The MAXQ Method for Hierarchical Reinforcement Learning. Thomas G. Dietterich. Department of Computer Science. Oregon State University. Corvallis, Oregon ... Pdfs.semanticscholar.org

State Abstraction in MAXQ Hierarchical Reinforcement Learning » ous work, we developed the MAXQ method for hierarchical RL. In… Most work on hierarchical reinforcement learning has focused on temporal abstrac- tion. Papers.nips.cc