Author:
Adolphs Leonard,Hofmann Thomas
Abstract
While Reinforcement Learning (RL) approaches lead to significant achievements in a variety of areas in recent history, natural language tasks remained mostly unaffected, due to the compositional and combinatorial nature that makes them notoriously hard to optimize. With the emerging field of Text-Based Games (TBGs), researchers try to bridge this gap. Inspired by the success of RL algorithms on Atari games, the idea is to develop new methods in a restricted game world and then gradually move to more complex environments. Previous work in the area of TBGs has mainly focused on solving individual games. We, however, consider the task of designing an agent that not just succeeds in a single game, but performs well across a whole family of games, sharing the same theme. In this work, we present our deep RL agent—LeDeepChef—that shows generalization capabilities to never-before-seen games of the same family with different environments and task descriptions. The agent participated in Microsoft Research's First TextWorld Problems: A Language and Reinforcement Learning Challenge and outperformed all but one competitor on the final test set. The games from the challenge all share the same theme, namely cooking in a modern house environment, but differ significantly in the arrangement of the rooms, the presented objects, and the specific goal (recipe to cook). To build an agent that achieves high scores across a whole family of games, we use an actor-critic framework and prune the action-space by using ideas from hierarchical reinforcement learning and a specialized module trained on a recipe database.
Publisher
Association for the Advancement of Artificial Intelligence (AAAI)
Cited by
6 articles.
订阅此论文施引文献
订阅此论文施引文献,注册后可以免费订阅5篇论文的施引文献,订阅后可以查看论文全部施引文献
1. Explaining crowdworker behaviour through computational rationality;Behaviour & Information Technology;2024-04-24
2. Leveraging Visual Handicaps for Text-Based Reinforcement Learning;ICASSP 2024 - 2024 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP);2024-04-14
3. Reinforcement Learning Algorithm of Intelligent Cultural and Creative Product Design Based on Data Mining Technology;2022 International Conference on Knowledge Engineering and Communication Systems (ICKES);2022-12-28
4. A Survey of Text Games for Reinforcement Learning Informed by Natural Language;Transactions of the Association for Computational Linguistics;2022
5. A Model-Based Exploration Policy in Deep Q-Network;2021 International Conference on Digital Society and Intelligent Systems (DSInS);2021-12-03