Reward Design for Deep Reinforcement Learning Towards Imparting Commonsense Knowledge in Text-Based Scenario

Ryota Kubo, Fumito Uwano, Manabu Ohta

2024

Abstract

In text-based reinforcement learning, an agent learns from text to make appropriate choices, with a focus on addressing challenges associated with imparting commonsense knowledge to the learning agent. The commonsense knowledge requires the agent to understand not only the context but also the meaning of textual data. However, the methodology has not been established, that is, the effects on the agents, state-action space, reward, and environment that constitute reinforcement learning are not revealed. This paper focused on the reward for the commonsense knowledge to propose a new reward design method on the existing learning framework called ScriptWorld. The experimental results let us discuss the influence of the reward on the acquisition of commonsense knowledge by reinforcement learning.

Paper Citation

in Harvard Style

Kubo R., Uwano F. and Ohta M. (2024). Reward Design for Deep Reinforcement Learning Towards Imparting Commonsense Knowledge in Text-Based Scenario. In Proceedings of the 16th International Conference on Agents and Artificial Intelligence - Volume 3: ICAART; ISBN 978-989-758-680-4, SciTePress, pages 1213-1220. DOI: 10.5220/0012456900003636

in Bibtex Style

@conference{icaart24,
author={Ryota Kubo and Fumito Uwano and Manabu Ohta},
title={Reward Design for Deep Reinforcement Learning Towards Imparting Commonsense Knowledge in Text-Based Scenario},
booktitle={Proceedings of the 16th International Conference on Agents and Artificial Intelligence - Volume 3: ICAART},
year={2024},
pages={1213-1220},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0012456900003636},
isbn={978-989-758-680-4},
}

in EndNote Style

TY - CONF

JO - Proceedings of the 16th International Conference on Agents and Artificial Intelligence - Volume 3: ICAART
TI - Reward Design for Deep Reinforcement Learning Towards Imparting Commonsense Knowledge in Text-Based Scenario
SN - 978-989-758-680-4
AU - Kubo R.
AU - Uwano F.
AU - Ohta M.
PY - 2024
SP - 1213
EP - 1220
DO - 10.5220/0012456900003636
PB - SciTePress