Matches in SemOpenAlex for { <https://semopenalex.org/work/W2893105945> ?p ?o ?g. }
Showing items 1 to 76 of
76
with 100 items per page.
- W2893105945 abstract "We propose a probabilistic framework to directly insert prior knowledge in reinforcement learning (RL) algorithms by defining the behaviour policy as a Bayesian posterior distribution. Such a posterior combines task specific information with prior knowledge, thus allowing to achieve transfer learning across tasks. The resulting method is flexible and it can be easily incorporated to any standard off-policy and on-policy algorithms, such as those based on temporal differences and policy gradients. We develop a specific instance of this Bayesian transfer RL framework by expressing prior knowledge as general deterministic rules that can be useful in a large variety of tasks, such as navigation tasks. Also, we elaborate more on recent probabilistic and entropy-regularised RL by developing a novel temporal learning algorithm and show how to combine it with Bayesian transfer RL. Finally, we demonstrate our method for solving mazes and show that significant speed ups can be obtained." @default.
- W2893105945 created "2018-10-05" @default.
- W2893105945 creator A5017255421 @default.
- W2893105945 creator A5042256748 @default.
- W2893105945 date "2018-09-30" @default.
- W2893105945 modified "2023-09-27" @default.
- W2893105945 title "Bayesian Transfer Reinforcement Learning with Prior Knowledge Rules." @default.
- W2893105945 cites W2294241375 @default.
- W2893105945 cites W2949608212 @default.
- W2893105945 hasPublicationYear "2018" @default.
- W2893105945 type Work @default.
- W2893105945 sameAs 2893105945 @default.
- W2893105945 citedByCount "1" @default.
- W2893105945 countsByYear W28931059452021 @default.
- W2893105945 crossrefType "posted-content" @default.
- W2893105945 hasAuthorship W2893105945A5017255421 @default.
- W2893105945 hasAuthorship W2893105945A5042256748 @default.
- W2893105945 hasConcept C106301342 @default.
- W2893105945 hasConcept C107673813 @default.
- W2893105945 hasConcept C119857082 @default.
- W2893105945 hasConcept C121332964 @default.
- W2893105945 hasConcept C136197465 @default.
- W2893105945 hasConcept C150899416 @default.
- W2893105945 hasConcept C154945302 @default.
- W2893105945 hasConcept C162324750 @default.
- W2893105945 hasConcept C177769412 @default.
- W2893105945 hasConcept C187736073 @default.
- W2893105945 hasConcept C2780451532 @default.
- W2893105945 hasConcept C41008148 @default.
- W2893105945 hasConcept C49937458 @default.
- W2893105945 hasConcept C62520636 @default.
- W2893105945 hasConcept C9679016 @default.
- W2893105945 hasConcept C97541855 @default.
- W2893105945 hasConceptScore W2893105945C106301342 @default.
- W2893105945 hasConceptScore W2893105945C107673813 @default.
- W2893105945 hasConceptScore W2893105945C119857082 @default.
- W2893105945 hasConceptScore W2893105945C121332964 @default.
- W2893105945 hasConceptScore W2893105945C136197465 @default.
- W2893105945 hasConceptScore W2893105945C150899416 @default.
- W2893105945 hasConceptScore W2893105945C154945302 @default.
- W2893105945 hasConceptScore W2893105945C162324750 @default.
- W2893105945 hasConceptScore W2893105945C177769412 @default.
- W2893105945 hasConceptScore W2893105945C187736073 @default.
- W2893105945 hasConceptScore W2893105945C2780451532 @default.
- W2893105945 hasConceptScore W2893105945C41008148 @default.
- W2893105945 hasConceptScore W2893105945C49937458 @default.
- W2893105945 hasConceptScore W2893105945C62520636 @default.
- W2893105945 hasConceptScore W2893105945C9679016 @default.
- W2893105945 hasConceptScore W2893105945C97541855 @default.
- W2893105945 hasLocation W28931059451 @default.
- W2893105945 hasOpenAccess W2893105945 @default.
- W2893105945 hasPrimaryLocation W28931059451 @default.
- W2893105945 hasRelatedWork W1013235724 @default.
- W2893105945 hasRelatedWork W2081725006 @default.
- W2893105945 hasRelatedWork W2622926601 @default.
- W2893105945 hasRelatedWork W2807352135 @default.
- W2893105945 hasRelatedWork W2891236810 @default.
- W2893105945 hasRelatedWork W2901329458 @default.
- W2893105945 hasRelatedWork W2948210913 @default.
- W2893105945 hasRelatedWork W2950182411 @default.
- W2893105945 hasRelatedWork W2951201424 @default.
- W2893105945 hasRelatedWork W2976371263 @default.
- W2893105945 hasRelatedWork W2984724235 @default.
- W2893105945 hasRelatedWork W2985059195 @default.
- W2893105945 hasRelatedWork W2987141291 @default.
- W2893105945 hasRelatedWork W2993852105 @default.
- W2893105945 hasRelatedWork W2998528009 @default.
- W2893105945 hasRelatedWork W3000554410 @default.
- W2893105945 hasRelatedWork W3174220719 @default.
- W2893105945 hasRelatedWork W3175944005 @default.
- W2893105945 hasRelatedWork W3200466256 @default.
- W2893105945 hasRelatedWork W47548177 @default.
- W2893105945 isParatext "false" @default.
- W2893105945 isRetracted "false" @default.
- W2893105945 magId "2893105945" @default.
- W2893105945 workType "article" @default.