Matches in SemOpenAlex for { <https://semopenalex.org/work/W4382319364> ?p ?o ?g. }
Showing items 1 to 93 of
93
with 100 items per page.
- W4382319364 abstract "We study a class of reinforcement learning (RL) tasks where the objective of the agent is to accomplish temporally extended goals. In this setting, a common approach is to represent the tasks as deterministic finite automata (DFA) and integrate them into the state-space for RL algorithms. However, while these machines model the reward function, they often overlook the causal knowledge about the environment. To address this limitation, we propose the Temporal-Logic-based Causal Diagram (TL-CD) in RL, which captures the temporal causal relationships between different properties of the environment. We exploit the TL-CD to devise an RL algorithm in which an agent requires significantly less exploration of the environment. To this end, based on a TL-CD and a task DFA, we identify configurations where the agent can determine the expected rewards early during an exploration. Through a series of case studies, we demonstrate the benefits of using TL-CDs, particularly the faster convergence of the algorithm to an optimal policy due to reduced exploration of the environment." @default.
- W4382319364 created "2023-06-28" @default.
- W4382319364 creator A5010315401 @default.
- W4382319364 creator A5013789785 @default.
- W4382319364 creator A5064701353 @default.
- W4382319364 creator A5065122789 @default.
- W4382319364 creator A5068441112 @default.
- W4382319364 creator A5074431546 @default.
- W4382319364 creator A5080724186 @default.
- W4382319364 creator A5092346339 @default.
- W4382319364 date "2023-06-23" @default.
- W4382319364 modified "2023-10-06" @default.
- W4382319364 title "Reinforcement Learning with Temporal-Logic-Based Causal Diagrams" @default.
- W4382319364 doi "https://doi.org/10.48550/arxiv.2306.13732" @default.
- W4382319364 hasPublicationYear "2023" @default.
- W4382319364 type Work @default.
- W4382319364 citedByCount "0" @default.
- W4382319364 crossrefType "posted-content" @default.
- W4382319364 hasAuthorship W4382319364A5010315401 @default.
- W4382319364 hasAuthorship W4382319364A5013789785 @default.
- W4382319364 hasAuthorship W4382319364A5064701353 @default.
- W4382319364 hasAuthorship W4382319364A5065122789 @default.
- W4382319364 hasAuthorship W4382319364A5068441112 @default.
- W4382319364 hasAuthorship W4382319364A5074431546 @default.
- W4382319364 hasAuthorship W4382319364A5080724186 @default.
- W4382319364 hasAuthorship W4382319364A5092346339 @default.
- W4382319364 hasBestOaLocation W43823193641 @default.
- W4382319364 hasConcept C105795698 @default.
- W4382319364 hasConcept C111919701 @default.
- W4382319364 hasConcept C112505250 @default.
- W4382319364 hasConcept C11413529 @default.
- W4382319364 hasConcept C14036430 @default.
- W4382319364 hasConcept C154945302 @default.
- W4382319364 hasConcept C162324750 @default.
- W4382319364 hasConcept C165696696 @default.
- W4382319364 hasConcept C167822520 @default.
- W4382319364 hasConcept C187736073 @default.
- W4382319364 hasConcept C25016198 @default.
- W4382319364 hasConcept C2777212361 @default.
- W4382319364 hasConcept C2777303404 @default.
- W4382319364 hasConcept C2778572836 @default.
- W4382319364 hasConcept C2780451532 @default.
- W4382319364 hasConcept C33923547 @default.
- W4382319364 hasConcept C38652104 @default.
- W4382319364 hasConcept C41008148 @default.
- W4382319364 hasConcept C48103436 @default.
- W4382319364 hasConcept C50522688 @default.
- W4382319364 hasConcept C72434380 @default.
- W4382319364 hasConcept C78458016 @default.
- W4382319364 hasConcept C80444323 @default.
- W4382319364 hasConcept C86803240 @default.
- W4382319364 hasConcept C97541855 @default.
- W4382319364 hasConceptScore W4382319364C105795698 @default.
- W4382319364 hasConceptScore W4382319364C111919701 @default.
- W4382319364 hasConceptScore W4382319364C112505250 @default.
- W4382319364 hasConceptScore W4382319364C11413529 @default.
- W4382319364 hasConceptScore W4382319364C14036430 @default.
- W4382319364 hasConceptScore W4382319364C154945302 @default.
- W4382319364 hasConceptScore W4382319364C162324750 @default.
- W4382319364 hasConceptScore W4382319364C165696696 @default.
- W4382319364 hasConceptScore W4382319364C167822520 @default.
- W4382319364 hasConceptScore W4382319364C187736073 @default.
- W4382319364 hasConceptScore W4382319364C25016198 @default.
- W4382319364 hasConceptScore W4382319364C2777212361 @default.
- W4382319364 hasConceptScore W4382319364C2777303404 @default.
- W4382319364 hasConceptScore W4382319364C2778572836 @default.
- W4382319364 hasConceptScore W4382319364C2780451532 @default.
- W4382319364 hasConceptScore W4382319364C33923547 @default.
- W4382319364 hasConceptScore W4382319364C38652104 @default.
- W4382319364 hasConceptScore W4382319364C41008148 @default.
- W4382319364 hasConceptScore W4382319364C48103436 @default.
- W4382319364 hasConceptScore W4382319364C50522688 @default.
- W4382319364 hasConceptScore W4382319364C72434380 @default.
- W4382319364 hasConceptScore W4382319364C78458016 @default.
- W4382319364 hasConceptScore W4382319364C80444323 @default.
- W4382319364 hasConceptScore W4382319364C86803240 @default.
- W4382319364 hasConceptScore W4382319364C97541855 @default.
- W4382319364 hasLocation W43823193641 @default.
- W4382319364 hasOpenAccess W4382319364 @default.
- W4382319364 hasPrimaryLocation W43823193641 @default.
- W4382319364 hasRelatedWork W2028415656 @default.
- W4382319364 hasRelatedWork W2143977190 @default.
- W4382319364 hasRelatedWork W2216182229 @default.
- W4382319364 hasRelatedWork W2226549490 @default.
- W4382319364 hasRelatedWork W2507321993 @default.
- W4382319364 hasRelatedWork W2604575008 @default.
- W4382319364 hasRelatedWork W2612831843 @default.
- W4382319364 hasRelatedWork W2973217651 @default.
- W4382319364 hasRelatedWork W3014472602 @default.
- W4382319364 hasRelatedWork W3087756144 @default.
- W4382319364 isParatext "false" @default.
- W4382319364 isRetracted "false" @default.
- W4382319364 workType "article" @default.