HQ-Learning-Reference-Cited by-同舟云学术

HQ-Learning

Published:1997-09 Issue:2 Volume:6 Page:219-246
ISSN:1059-7123
Container-title:Adaptive Behavior
language:en
Short-container-title:Adaptive Behavior

Author:

Wiering Marco¹,Schmidhuber Jürgen¹

Affiliation:

1. Istituto Dalle Molle di Studi sull'Intelligenza Artificiale

Abstract

HQ-learning is a hierarchical extension of Q(λ)-learning designed to solve certain types of partially observable Markov decision problems (POMDPs). HQ automatically decomposes POMDPs into sequences of simpler subtasks that can be solved by memoryless policies learnable by reactive subagents. HQ can solve partially observable mazes with more states than those used in most previous POMDP work.

Publisher

SAGE Publications

Subject

Behavioral Neuroscience,Experimental and Cognitive Psychology

Link

http://journals.sagepub.com/doi/pdf/10.1177/105971239700600202

Reference53 articles.

1. Adding Temporary Memory to ZCS

2. Neural Network Exploration Using Optional Experiment Design,

Cited by 87 articles. 订阅此论文施引文献订阅此论文施引文献，注册后可以免费订阅5篇论文的施引文献，订阅后可以查看论文全部施引文献

1. A hybrid connectionist/LCS for hidden-state problems;Neural Computing and Applications;2024-04-22

2. Faster MIL-based Subgoal Identification for Reinforcement Learning by Tuning Fewer Hyperparameters;ACM Transactions on Autonomous and Adaptive Systems;2024-04-20

3. Learning to Identify Critical States for Reinforcement Learning from Videos;2023 IEEE/CVF International Conference on Computer Vision (ICCV);2023-10-01

4. Sophisticated Swarm Reinforcement Learning by Incorporating Inverse Reinforcement Learning;2023 IEEE International Conference on Systems, Man, and Cybernetics (SMC);2023-10-01

5. Hierarchical Model-Based Deep Reinforcement Learning for Single-Asset Trading;Analytics;2023-07-11