Title:
Language Learning in Interactive Environments
Language Learning in Interactive Environments
dc.contributor.advisor | Riedl, Mark O. | |
dc.contributor.author | Ammanabrolu, Prithviraj Venkata | |
dc.contributor.committeeMember | Isbell, Charles | |
dc.contributor.committeeMember | Parikh, Devi | |
dc.contributor.committeeMember | Hausknecht, Matthew | |
dc.contributor.committeeMember | Weston, Jason | |
dc.contributor.department | Interactive Computing | |
dc.date.accessioned | 2021-09-15T15:44:01Z | |
dc.date.available | 2021-09-15T15:44:01Z | |
dc.date.created | 2021-08 | |
dc.date.issued | 2021-07-28 | |
dc.date.submitted | August 2021 | |
dc.date.updated | 2021-09-15T15:44:02Z | |
dc.description.abstract | Natural language communication has long been considered a defining characteristic of human intelligence. I am motivated by the question of how learning agents can understand and generate contextually relevant natural language in service of achieving a goal. In pursuit of this objective, I have been studying Interactive Narratives, or text-adventures: simulations in which an agent interacts with the world purely through natural language—"seeing” and “acting upon” the world using textual descriptions and commands. These games are usually structured as puzzles or quests in which a player must complete a sequence of actions to succeed. My work studies two closely related aspects of Interactive Narratives: operating in these environments and creating them in addition to their intersection—each presenting its own set of unique challenges. Operating in these environments presents three challenges: (1) Knowledge representation—an agent must maintain a persistent memory of what it has learned through its experiences with a partially observable world; (2) Commonsense reasoning to endow the agent with priors on how to interact with the world around it; and (3) Scaling to effectively explore sparse-reward, combinatorially-sized natural language state-action spaces. On the other hand, creating these environments can be split into two complementary considerations: (1) World generation, or the problem of creating a world that defines the limits of the actions an agent can perform; and (2) Quest generation, i.e. defining actionable objectives grounded in a given world. I will present my work thus far—showcasing how structured, interpretable data representations in the form of knowledge graphs aid in each of these tasks—in addition to proposing how exactly these two aspects of Interactive Narratives can be combined to improve language learning and generalization across this board of challenges. | |
dc.description.degree | Ph.D. | |
dc.format.mimetype | application/pdf | |
dc.identifier.uri | http://hdl.handle.net/1853/65088 | |
dc.language.iso | en_US | |
dc.publisher | Georgia Institute of Technology | |
dc.subject | Natural Language Processing | |
dc.subject | Reinforcement Learning | |
dc.subject | Computational Creativity | |
dc.subject | Knowledge Graphs | |
dc.subject | Interactive Narratives | |
dc.title | Language Learning in Interactive Environments | |
dc.type | Text | |
dc.type.genre | Dissertation | |
dspace.entity.type | Publication | |
local.contributor.advisor | Riedl, Mark O. | |
local.contributor.corporatename | College of Computing | |
local.contributor.corporatename | School of Interactive Computing | |
relation.isAdvisorOfPublication | 6512b353-3315-4dd1-9f47-7aaef3e19300 | |
relation.isOrgUnitOfPublication | c8892b3c-8db6-4b7b-a33a-1b67f7db2021 | |
relation.isOrgUnitOfPublication | aac3f010-e629-4d08-8276-81143eeaf5cc | |
thesis.degree.level | Doctoral |