Context tree maximizing reinforcement learning

Loading...
Thumbnail Image

Date

Authors

Nguyen, Phuong
Sunehag, Peter
Hutter, Marcus

Journal Title

Journal ISSN

Volume Title

Publisher

AAAI Press

Abstract

Recent developments in reinforcement learning for non-Markovian problems witness a surge in history-based methods, among which we are particularly interested in two frameworks, ΦMDP and MC-AIXI-CTW. ΦMDP attempts to reduce the general RL problem, where

Description

Citation

Source

Proceedings of the National Conference on Artificial Intelligence

Book Title

Entity type

Access Statement

License Rights

DOI

Restricted until

2037-12-31