Matches in SemOpenAlex for { <https://semopenalex.org/work/W4387394578> ?p ?o ?g. }
Showing items 1 to 79 of
79
with 100 items per page.
- W4387394578 endingPage "336" @default.
- W4387394578 startingPage "326" @default.
- W4387394578 abstract "Reward design for reinforcement learning agents can be difficult in situations where one not only wants the agent to achieve some effect in the world but where one also cares about how that effect is achieved. For example, we might wish for an agent to adhere to a tacit understanding of commonsense, align itself to a preference for how to behave for purposes of safety, or taking on a particular role in an interactive game. Storytelling is a mode for communicating tacit procedural knowledge. We introduce a technique, Story Shaping, in which a reinforcement learning agent infers tacit knowledge from an exemplar story of how to accomplish a task and intrinsically rewards itself for performing actions that make its current environment adhere to that of the inferred story world. Specifically, Story Shaping infers a knowledge graph representation of the world state from observations, and also infers a knowledge graph from the exemplar story. An intrinsic reward is generated based on the similarity between the agent's inferred world state graph and the inferred story world graph. We conducted experiments in text-based games requiring commonsense reasoning and shaping the behaviors of agents as virtual game characters." @default.
- W4387394578 created "2023-10-07" @default.
- W4387394578 creator A5009723141 @default.
- W4387394578 creator A5018457347 @default.
- W4387394578 creator A5026119563 @default.
- W4387394578 creator A5061883150 @default.
- W4387394578 creator A5081125869 @default.
- W4387394578 date "2023-10-06" @default.
- W4387394578 modified "2023-10-07" @default.
- W4387394578 title "Story Shaping: Teaching Agents Human-Like Behavior with Stories" @default.
- W4387394578 doi "https://doi.org/10.1609/aiide.v19i1.27528" @default.
- W4387394578 hasPublicationYear "2023" @default.
- W4387394578 type Work @default.
- W4387394578 citedByCount "0" @default.
- W4387394578 crossrefType "journal-article" @default.
- W4387394578 hasAuthorship W4387394578A5009723141 @default.
- W4387394578 hasAuthorship W4387394578A5018457347 @default.
- W4387394578 hasAuthorship W4387394578A5026119563 @default.
- W4387394578 hasAuthorship W4387394578A5061883150 @default.
- W4387394578 hasAuthorship W4387394578A5081125869 @default.
- W4387394578 hasBestOaLocation W43873945781 @default.
- W4387394578 hasConcept C107457646 @default.
- W4387394578 hasConcept C132525143 @default.
- W4387394578 hasConcept C138885662 @default.
- W4387394578 hasConcept C154945302 @default.
- W4387394578 hasConcept C15744967 @default.
- W4387394578 hasConcept C161301231 @default.
- W4387394578 hasConcept C162324750 @default.
- W4387394578 hasConcept C187736073 @default.
- W4387394578 hasConcept C188147891 @default.
- W4387394578 hasConcept C199033989 @default.
- W4387394578 hasConcept C2776538412 @default.
- W4387394578 hasConcept C2779561248 @default.
- W4387394578 hasConcept C2780451532 @default.
- W4387394578 hasConcept C30542707 @default.
- W4387394578 hasConcept C41008148 @default.
- W4387394578 hasConcept C41895202 @default.
- W4387394578 hasConcept C56739046 @default.
- W4387394578 hasConcept C80444323 @default.
- W4387394578 hasConcept C97541855 @default.
- W4387394578 hasConceptScore W4387394578C107457646 @default.
- W4387394578 hasConceptScore W4387394578C132525143 @default.
- W4387394578 hasConceptScore W4387394578C138885662 @default.
- W4387394578 hasConceptScore W4387394578C154945302 @default.
- W4387394578 hasConceptScore W4387394578C15744967 @default.
- W4387394578 hasConceptScore W4387394578C161301231 @default.
- W4387394578 hasConceptScore W4387394578C162324750 @default.
- W4387394578 hasConceptScore W4387394578C187736073 @default.
- W4387394578 hasConceptScore W4387394578C188147891 @default.
- W4387394578 hasConceptScore W4387394578C199033989 @default.
- W4387394578 hasConceptScore W4387394578C2776538412 @default.
- W4387394578 hasConceptScore W4387394578C2779561248 @default.
- W4387394578 hasConceptScore W4387394578C2780451532 @default.
- W4387394578 hasConceptScore W4387394578C30542707 @default.
- W4387394578 hasConceptScore W4387394578C41008148 @default.
- W4387394578 hasConceptScore W4387394578C41895202 @default.
- W4387394578 hasConceptScore W4387394578C56739046 @default.
- W4387394578 hasConceptScore W4387394578C80444323 @default.
- W4387394578 hasConceptScore W4387394578C97541855 @default.
- W4387394578 hasIssue "1" @default.
- W4387394578 hasLocation W43873945781 @default.
- W4387394578 hasOpenAccess W4387394578 @default.
- W4387394578 hasPrimaryLocation W43873945781 @default.
- W4387394578 hasRelatedWork W1536421369 @default.
- W4387394578 hasRelatedWork W1765898938 @default.
- W4387394578 hasRelatedWork W2082193010 @default.
- W4387394578 hasRelatedWork W2086118318 @default.
- W4387394578 hasRelatedWork W2355818213 @default.
- W4387394578 hasRelatedWork W2884441370 @default.
- W4387394578 hasRelatedWork W2993120730 @default.
- W4387394578 hasRelatedWork W4319988281 @default.
- W4387394578 hasRelatedWork W4320006770 @default.
- W4387394578 hasRelatedWork W66522602 @default.
- W4387394578 hasVolume "19" @default.
- W4387394578 isParatext "false" @default.
- W4387394578 isRetracted "false" @default.
- W4387394578 workType "article" @default.