Efficient Text-based Reinforcement Learning by Jointly Leveraging State and Commonsense Graph Representations
Keerthiram Murugesan, Mattia Atzeni, Pavan Kapanipathi, Kartik Talamadupula, Mrinmaya Sachan, Murray Campbell
Abstract
Text-based games (TBGs) have emerged as useful benchmarks for evaluating progress at the intersection of grounded language understanding and reinforcement learning (RL). Recent work has proposed the use of external knowledge to improve the efficiency of RL agents for TBGs. In this paper, we posit that to act efficiently in TBGs, an agent must be able to track the state of the game while retrieving and using relevant commonsense knowledge. Thus, we propose an agent for TBGs that induces a graph representation of the game state and jointly grounds it with a graph of commonsense knowledge from ConceptNet. This combination is achieved through bidirectional knowledge graph attention between the two symbolic representations. We show that agents that incorporate commonsense into the game state graph outperform baseline agents.
BibTeX
@inproceedings{murugesan-etal-2021-efficient,
title = "Efficient Text-based Reinforcement Learning by Jointly Leveraging State and Commonsense Graph Representations",
author = "Murugesan, Keerthiram and
Atzeni, Mattia and
Kapanipathi, Pavan and
Talamadupula, Kartik and
Sachan, Mrinmaya and
Campbell, Murray",
editor = "Zong, Chengqing and
Xia, Fei and
Li, Wenjie and
Navigli, Roberto",
booktitle = "Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing (Volume 2: Short Papers)",
month = aug,
year = "2021",
address = "Online",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2021.acl-short.91/",
doi = "10.18653/v1/2021.acl-short.91",
pages = "719--725"
}