Matches in SemOpenAlex for { <https://semopenalex.org/work/W2996887765> ?p ?o ?g. }
Showing items 1 to 94 of
94
with 100 items per page.
- W2996887765 endingPage "7349" @default.
- W2996887765 startingPage "7342" @default.
- W2996887765 abstract "While Reinforcement Learning (RL) approaches lead to significant achievements in a variety of areas in recent history, natural language tasks remained mostly unaffected, due to the compositional and combinatorial nature that makes them notoriously hard to optimize. With the emerging field of Text-Based Games (TBGs), researchers try to bridge this gap. Inspired by the success of RL algorithms on Atari games, the idea is to develop new methods in a restricted game world and then gradually move to more complex environments. Previous work in the area of TBGs has mainly focused on solving individual games. We, however, consider the task of designing an agent that not just succeeds in a single game, but performs well across a whole family of games, sharing the same theme. In this work, we present our deep RL agent—LeDeepChef—that shows generalization capabilities to never-before-seen games of the same family with different environments and task descriptions. The agent participated in Microsoft Research's First TextWorld Problems: A Language and Reinforcement Learning Challenge and outperformed all but one competitor on the final test set. The games from the challenge all share the same theme, namely cooking in a modern house environment, but differ significantly in the arrangement of the rooms, the presented objects, and the specific goal (recipe to cook). To build an agent that achieves high scores across a whole family of games, we use an actor-critic framework and prune the action-space by using ideas from hierarchical reinforcement learning and a specialized module trained on a recipe database." @default.
- W2996887765 created "2020-01-10" @default.
- W2996887765 creator A5001786495 @default.
- W2996887765 creator A5045413165 @default.
- W2996887765 date "2020-04-03" @default.
- W2996887765 modified "2023-10-17" @default.
- W2996887765 title "LeDeepChef Deep Reinforcement Learning Agent for Families of Text-Based Games" @default.
- W2996887765 doi "https://doi.org/10.1609/aaai.v34i05.6228" @default.
- W2996887765 hasPublicationYear "2020" @default.
- W2996887765 type Work @default.
- W2996887765 sameAs 2996887765 @default.
- W2996887765 citedByCount "22" @default.
- W2996887765 countsByYear W29968877652019 @default.
- W2996887765 countsByYear W29968877652020 @default.
- W2996887765 countsByYear W29968877652021 @default.
- W2996887765 countsByYear W29968877652022 @default.
- W2996887765 crossrefType "journal-article" @default.
- W2996887765 hasAuthorship W2996887765A5001786495 @default.
- W2996887765 hasAuthorship W2996887765A5045413165 @default.
- W2996887765 hasBestOaLocation W29968877651 @default.
- W2996887765 hasConcept C100776233 @default.
- W2996887765 hasConcept C107457646 @default.
- W2996887765 hasConcept C111919701 @default.
- W2996887765 hasConcept C126322002 @default.
- W2996887765 hasConcept C127413603 @default.
- W2996887765 hasConcept C134306372 @default.
- W2996887765 hasConcept C136197465 @default.
- W2996887765 hasConcept C136764020 @default.
- W2996887765 hasConcept C154945302 @default.
- W2996887765 hasConcept C15744967 @default.
- W2996887765 hasConcept C177148314 @default.
- W2996887765 hasConcept C177264268 @default.
- W2996887765 hasConcept C199360897 @default.
- W2996887765 hasConcept C201995342 @default.
- W2996887765 hasConcept C202444582 @default.
- W2996887765 hasConcept C2777212361 @default.
- W2996887765 hasConcept C2778572836 @default.
- W2996887765 hasConcept C2780451532 @default.
- W2996887765 hasConcept C33566652 @default.
- W2996887765 hasConcept C33923547 @default.
- W2996887765 hasConcept C41008148 @default.
- W2996887765 hasConcept C67203356 @default.
- W2996887765 hasConcept C71924100 @default.
- W2996887765 hasConcept C77805123 @default.
- W2996887765 hasConcept C9652623 @default.
- W2996887765 hasConcept C97541855 @default.
- W2996887765 hasConceptScore W2996887765C100776233 @default.
- W2996887765 hasConceptScore W2996887765C107457646 @default.
- W2996887765 hasConceptScore W2996887765C111919701 @default.
- W2996887765 hasConceptScore W2996887765C126322002 @default.
- W2996887765 hasConceptScore W2996887765C127413603 @default.
- W2996887765 hasConceptScore W2996887765C134306372 @default.
- W2996887765 hasConceptScore W2996887765C136197465 @default.
- W2996887765 hasConceptScore W2996887765C136764020 @default.
- W2996887765 hasConceptScore W2996887765C154945302 @default.
- W2996887765 hasConceptScore W2996887765C15744967 @default.
- W2996887765 hasConceptScore W2996887765C177148314 @default.
- W2996887765 hasConceptScore W2996887765C177264268 @default.
- W2996887765 hasConceptScore W2996887765C199360897 @default.
- W2996887765 hasConceptScore W2996887765C201995342 @default.
- W2996887765 hasConceptScore W2996887765C202444582 @default.
- W2996887765 hasConceptScore W2996887765C2777212361 @default.
- W2996887765 hasConceptScore W2996887765C2778572836 @default.
- W2996887765 hasConceptScore W2996887765C2780451532 @default.
- W2996887765 hasConceptScore W2996887765C33566652 @default.
- W2996887765 hasConceptScore W2996887765C33923547 @default.
- W2996887765 hasConceptScore W2996887765C41008148 @default.
- W2996887765 hasConceptScore W2996887765C67203356 @default.
- W2996887765 hasConceptScore W2996887765C71924100 @default.
- W2996887765 hasConceptScore W2996887765C77805123 @default.
- W2996887765 hasConceptScore W2996887765C9652623 @default.
- W2996887765 hasConceptScore W2996887765C97541855 @default.
- W2996887765 hasIssue "05" @default.
- W2996887765 hasLocation W29968877651 @default.
- W2996887765 hasLocation W29968877652 @default.
- W2996887765 hasOpenAccess W2996887765 @default.
- W2996887765 hasPrimaryLocation W29968877651 @default.
- W2996887765 hasRelatedWork W2005465051 @default.
- W2996887765 hasRelatedWork W2031527081 @default.
- W2996887765 hasRelatedWork W2047937115 @default.
- W2996887765 hasRelatedWork W2951308022 @default.
- W2996887765 hasRelatedWork W3139321261 @default.
- W2996887765 hasRelatedWork W3183432322 @default.
- W2996887765 hasRelatedWork W320167972 @default.
- W2996887765 hasRelatedWork W4288317198 @default.
- W2996887765 hasRelatedWork W4293469469 @default.
- W2996887765 hasRelatedWork W4302011254 @default.
- W2996887765 hasVolume "34" @default.
- W2996887765 isParatext "false" @default.
- W2996887765 isRetracted "false" @default.
- W2996887765 magId "2996887765" @default.
- W2996887765 workType "article" @default.