Bikramjit Banerjee's Publications
• Selected Publications • All Sorted by Date • All Classified by Publication Type •
On-Policy Concurrent Reinforcement Learning
Bikramjit Banerjee, Sandip Sen, and Jing Peng. On-Policy Concurrent Reinforcement Learning. Journal of Experimental and Theoretical Artificial Intelligence, 16(4):245 – 260, 2004.
Download
Abstract
When an agent learns in a multi-agent environment, the payoff it receives is dependent on the behaviour of the other agents. If the other agents are also learning, its reward distribution becomes non-stationary. This makes learning in multi-agent systems more difficult than single-agent learning. Prior attempts at value-function based learning in such domains have used off-policy Q-learning that do not scale well as the cornerstone, with restricted success. This paper studies on-policy modifications of such algorithms, with the promise of scalability and efficiency. In particular, it is proven that these hybrid techniques are guaranteed to converge to their desired fixed points under some restrictions. It is also shown, experimentally, that the new techniques can learn (from self-play) better policies than the previous algorithms (also in self-play) during some phases of the exploration.
BibTeX
@Article{Banerjee04:On-Policy,
author = {Bikramjit Banerjee and Sandip Sen and Jing Peng},
title = {On-Policy Concurrent Reinforcement Learning},
journal = {Journal of Experimental and Theoretical Artificial
Intelligence},
year = {2004},
volume = {16},
number = {4},
pages = {245 - 260},
abstract = {When an agent learns in a multi-agent environment, the
payoff it receives is dependent on the behaviour of the other agents.
If the other agents are also learning, its reward distribution becomes
non-stationary. This makes learning in multi-agent systems more
difficult than single-agent learning. Prior attempts at value-function
based learning in such domains have used off-policy Q-learning that do
not scale well as the cornerstone, with restricted success. This paper
studies on-policy modifications of such algorithms, with the promise of
scalability and efficiency. In particular, it is proven that these
hybrid techniques are guaranteed to converge to their desired fixed
points under some restrictions. It is also shown, experimentally, that
the new techniques can learn (from self-play) better policies than the
previous algorithms (also in self-play) during some phases of the
exploration.},
}
Generated by bib2html.pl (written by Patrick Riley ) on Sat May 29, 2021 15:48:22