Opponent Modeling in Deep Reinforcement Learning
He He, Jordan Boyd-Graber, Kevin Kwok, Hal Daumé III
Abstract
Opponent modeling is necessary in multi-agent settings where secondary agents with competing goals also adapt their strategies, yet it remains challenging because of strategies’ complex interaction and the non-stationary nature. Most previous work focuses on developing probabilistic models or parameterized strategies for specific applications. Inspired by the recent success of deep reinforcement learning, we present neural-based models that jointly learn a policy and the behavior of opponents. Instead of explicitly predicting the opponent’s action, we encode observation of the opponents into a deep Q-Network (DQN), while retaining explicit modeling under multitasking. By using a Mixture-of-Experts architecture, our model automatically discovers different strategy patterns of opponents even without extra supervision. We evaluate our models on a simulated soccer game and a popular trivia game, showing superior performance over DQN and its variants.
BibTeX
@InProceedings{pmlr-v48-he16,
title = {Opponent Modeling in Deep Reinforcement Learning},
author = {He, He and Boyd-Graber, Jordan and Kwok, Kevin and Daum\'e, III, Hal},
booktitle = {Proceedings of The 33rd International Conference on Machine Learning},
pages = {1804--1813},
year = {2016},
editor = {Balcan, Maria Florina and Weinberger, Kilian Q.},
volume = {48},
series = {Proceedings of Machine Learning Research},
address = {New York, New York, USA},
month = {20--22 Jun},
publisher = {PMLR},
pdf = {http://proceedings.mlr.press/v48/he16.pdf},
url = {https://proceedings.mlr.press/v48/he16.html},
abstract = {Opponent modeling is necessary in multi-agent settings where secondary agents with competing goals also adapt their strategies, yet it remains challenging because of strategies’ complex interaction and the non-stationary nature. Most previous work focuses on developing probabilistic models or parameterized strategies for specific applications. Inspired by the recent success of deep reinforcement learning, we present neural-based models that jointly learn a policy and the behavior of opponents. Instead of explicitly predicting the opponent’s action, we encode observation of the opponents into a deep Q-Network (DQN), while retaining explicit modeling under multitasking. By using a Mixture-of-Experts architecture, our model automatically discovers different strategy patterns of opponents even without extra supervision. We evaluate our models on a simulated soccer game and a popular trivia game, showing superior performance over DQN and its variants.}
}