Recent advances in hierarchical reinforcement learning (Q5917501)
From MaRDI portal
!
This is the item page for this Wikibase entity, intended for internal use and editing purposes. Please use the normal view instead:
scientific article; zbMATH DE number 1908597
| Language | Label | Description | Also known as |
|---|---|---|---|
| default for all languages | No label defined |
||
| English | Recent advances in hierarchical reinforcement learning |
scientific article; zbMATH DE number 1908597 |
Statements
Recent advances in hierarchical reinforcement learning (English)
0 references
11 May 2003
0 references
This paper reviews several closely related approaches to temporal abstraction and hierarchical control that have been developed by machine learning researchers: the options formalism of Sutton, Precup, and Singh, the hierarchies of abstract machines (HAMs) approach of Parr and Russell, and Dietterich's MAXQ framework. The authors also discuss extensions of these ideas addressing on concurrent activities, multiagent coordination, and hierarchical memory for partial observability.
0 references
reinforcement learning
0 references
hierarchies of abstract machines
0 references
hierarchical control
0 references
temporal abstraction
0 references
concurrency
0 references
options formalism
0 references
MAXQ framework
0 references
multiagent coordination
0 references
hierarchical memory
0 references
partial observability
0 references
0.9275484681129456
0 references
0.855442464351654
0 references
