Ryan Volum, Sudha Rao, Michael Xu, Gabriel DesGarennes, Chris Brockett, Benjamin Van Durme, O. Deng, Akanksha Malhotra, Bill Dolan
{"title":"Craft an Iron Sword: Dynamically Generating Interactive Game Characters by Prompting Large Language Models Tuned on Code","authors":"Ryan Volum, Sudha Rao, Michael Xu, Gabriel DesGarennes, Chris Brockett, Benjamin Van Durme, O. Deng, Akanksha Malhotra, Bill Dolan","doi":"10.18653/v1/2022.wordplay-1.3","DOIUrl":"https://doi.org/10.18653/v1/2022.wordplay-1.3","url":null,"abstract":"Non-Player Characters (NPCs) significantly enhance the player experience in many games. Historically, players’ interactions with NPCs have tended to be highly scripted, to be limited to natural language responses to be selected by the player, and to not involve dynamic change in game state. In this work, we demonstrate that use of a few example conversational prompts can power a conversational agent to generate both natural language and novel code. This approach can permit development of NPCs with which players can have grounded conversations that are free-form and less repetitive. We demonstrate our approach using OpenAI Codex (GPT-3 finetuned on GitHub), with Minecraft game development as our test bed. We show that with a few example prompts, a Codex-based agent can generate novel code, hold multi-turn conversations and answer questions about structured data. We evaluate this application using experienced gamers in a Minecraft realm and provide analysis of failure cases and suggest possible directions for solutions.","PeriodicalId":440244,"journal":{"name":"Proceedings of the 3rd Wordplay: When Language Meets Games Workshop (Wordplay 2022)","volume":"82 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1900-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125395366","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Gregory Furman, Edan Toledo, Jonathan Shock, Jan Buys
{"title":"A Sequence Modelling Approach to Question Answering in Text-Based Games","authors":"Gregory Furman, Edan Toledo, Jonathan Shock, Jan Buys","doi":"10.18653/v1/2022.wordplay-1.4","DOIUrl":"https://doi.org/10.18653/v1/2022.wordplay-1.4","url":null,"abstract":"Interactive Question Answering (IQA) requires an intelligent agent to interact with a dynamic environment in order to gather information necessary to answer a question. IQA tasks have been proposed as means of training systems to develop language or visual comprehension abilities. To this end, the Question Answering with Interactive Text (QAit) task was created to produce and benchmark interactive agents capable of seeking information and answering questions in unseen environments. While prior work has exclusively focused on IQA as a reinforcement learning problem, such methods suffer from low sample efficiency and poor accuracy in zero-shot evaluation. In this paper, we propose the use of the recently proposed Decision Transformer architecture to provide improvements upon prior baselines. By utilising a causally masked GPT-2 Transformer for command generation and a BERT model for question answer prediction, we show that the Decision Transformer achieves performance greater than or equal to current state-of-the-art RL baselines on the QAit task in a sample efficient manner. In addition, these results are achievable by training on sub-optimal random trajectories, therefore not requiring the use of online agents to gather data.","PeriodicalId":440244,"journal":{"name":"Proceedings of the 3rd Wordplay: When Language Meets Games Workshop (Wordplay 2022)","volume":"9 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1900-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121813580","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
{"title":"A Minimal Computational Improviser Based on Oral Thought","authors":"Nick Montfort, Sebastian Bartlett Fernandez","doi":"10.18653/v1/2022.wordplay-1.2","DOIUrl":"https://doi.org/10.18653/v1/2022.wordplay-1.2","url":null,"abstract":"A prototype system for playing a minimal improvisational game with one or more human or computer players is discussed. The game, Chain Reaction, has players collectively build a chain of word pairs or solid compounds. With a basis in oral culture, it emphasizes memory and rapid improvisation. Chains are only locally coherent, so absurdity and humor increases during play. While it is trivial to develop a computer player using textual corpora and literature-culture concepts, our approach is unique in that we have grounded our work in the principles of oral culture according to Walter Ong, an early scholar of orature. We show how a simple computer model can be designed to embody many aspects of oral poetics as theorized by Ong, suggesting design directions for other work in oral improvisation and poetics. The opportunities for own our system’s further development include creating culturally specific automated players and situating play in different temporal, physical, and social contexts.","PeriodicalId":440244,"journal":{"name":"Proceedings of the 3rd Wordplay: When Language Meets Games Workshop (Wordplay 2022)","volume":"65 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1900-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130621410","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}