Baselines for Reinforcement Learning in Text Games
This work provides a baseline for future research in reinforcement learning for text games, addressing the need for generalizable AI agents in this domain, though it is incremental in nature.
The authors tackled the problem of learning control policies in text-based games with natural language action spaces, presenting a minimalistic agent that demonstrates generalization to unseen games and transfer learning across multiple games.
The ability to learn optimal control policies in systems where action space is defined by sentences in natural language would allow many interesting real-world applications such as automatic optimisation of dialogue systems. Text-based games with multiple endings and rewards are a promising platform for this task, since their feedback allows us to employ reinforcement learning techniques to jointly learn text representations and control policies. We argue that the key property of AI agents, especially in the text-games context, is their ability to generalise to previously unseen games. We present a minimalistic text-game playing agent, testing its generalisation and transfer learning performance and showing its ability to play multiple games at once. We also present pyfiction, an open-source library for universal access to different text games that could, together with our agent that implements its interface, serve as a baseline for future research.