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 present a general 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.
| Identifer | oai:union.ndltd.org:nusl.cz/oai:invenio.nusl.cz:365188 |
| Date | January 2017 |
| Creators | Zelinka, Mikuláš |
| Contributors | Kadlec, Rudolf, Lisý, Viliam |
| Source Sets | Czech ETDs |
| Language | English |
| Detected Language | English |
| Type | info:eu-repo/semantics/masterThesis |
| Rights | info:eu-repo/semantics/restrictedAccess |
Page generated in 0.0017 seconds