Matches in SemOpenAlex for { <https://semopenalex.org/work/W2780123820> ?p ?o ?g. }
Showing items 1 to 74 of
74
with 100 items per page.
- W2780123820 abstract "With the increase of machine learning usage by industries and scientific communities in a variety of tasks such as text mining, image recognition and self-driving cars, automatic setting of hyper-parameter in learning algorithms is a key factor for achieving satisfactory performance regardless of user expertise in the inner workings of the techniques and methodologies. In particular, for a reinforcement learning algorithm, the efficiency of an agent learning a control policy in an uncertain environment is heavily dependent on the hyper-parameters used to balance exploration with exploitation. In this work, an autonomous learning framework that integrates Bayesian optimization with Gaussian process regression to optimize the hyper-parameters of a reinforcement learning algorithm, is proposed. Also, a bandits-based approach to achieve a balance between computational costs and decreasing uncertainty about the Q-values, is presented. A gridworld example is used to highlight how hyper-parameter configurations of a learning algorithm (SARSA) are iteratively improved based on two performance functions." @default.
- W2780123820 created "2018-01-05" @default.
- W2780123820 creator A5031625095 @default.
- W2780123820 creator A5031875872 @default.
- W2780123820 creator A5051112794 @default.
- W2780123820 date "2018-05-12" @default.
- W2780123820 modified "2023-10-14" @default.
- W2780123820 title "Towards Autonomous Reinforcement Learning: Automatic Setting of Hyper-parameters using Bayesian Optimization" @default.
- W2780123820 hasPublicationYear "2018" @default.
- W2780123820 type Work @default.
- W2780123820 sameAs 2780123820 @default.
- W2780123820 citedByCount "1" @default.
- W2780123820 countsByYear W27801238202019 @default.
- W2780123820 crossrefType "posted-content" @default.
- W2780123820 hasAuthorship W2780123820A5031625095 @default.
- W2780123820 hasAuthorship W2780123820A5031875872 @default.
- W2780123820 hasAuthorship W2780123820A5051112794 @default.
- W2780123820 hasConcept C107673813 @default.
- W2780123820 hasConcept C111919701 @default.
- W2780123820 hasConcept C119857082 @default.
- W2780123820 hasConcept C121332964 @default.
- W2780123820 hasConcept C154945302 @default.
- W2780123820 hasConcept C163716315 @default.
- W2780123820 hasConcept C26517878 @default.
- W2780123820 hasConcept C2778049539 @default.
- W2780123820 hasConcept C38652104 @default.
- W2780123820 hasConcept C41008148 @default.
- W2780123820 hasConcept C61326573 @default.
- W2780123820 hasConcept C62520636 @default.
- W2780123820 hasConcept C81692654 @default.
- W2780123820 hasConcept C97541855 @default.
- W2780123820 hasConcept C98045186 @default.
- W2780123820 hasConceptScore W2780123820C107673813 @default.
- W2780123820 hasConceptScore W2780123820C111919701 @default.
- W2780123820 hasConceptScore W2780123820C119857082 @default.
- W2780123820 hasConceptScore W2780123820C121332964 @default.
- W2780123820 hasConceptScore W2780123820C154945302 @default.
- W2780123820 hasConceptScore W2780123820C163716315 @default.
- W2780123820 hasConceptScore W2780123820C26517878 @default.
- W2780123820 hasConceptScore W2780123820C2778049539 @default.
- W2780123820 hasConceptScore W2780123820C38652104 @default.
- W2780123820 hasConceptScore W2780123820C41008148 @default.
- W2780123820 hasConceptScore W2780123820C61326573 @default.
- W2780123820 hasConceptScore W2780123820C62520636 @default.
- W2780123820 hasConceptScore W2780123820C81692654 @default.
- W2780123820 hasConceptScore W2780123820C97541855 @default.
- W2780123820 hasConceptScore W2780123820C98045186 @default.
- W2780123820 hasLocation W27801238201 @default.
- W2780123820 hasOpenAccess W2780123820 @default.
- W2780123820 hasPrimaryLocation W27801238201 @default.
- W2780123820 hasRelatedWork W1542791965 @default.
- W2780123820 hasRelatedWork W1562044912 @default.
- W2780123820 hasRelatedWork W1804739212 @default.
- W2780123820 hasRelatedWork W2001512991 @default.
- W2780123820 hasRelatedWork W2082582741 @default.
- W2780123820 hasRelatedWork W2139586486 @default.
- W2780123820 hasRelatedWork W2143680741 @default.
- W2780123820 hasRelatedWork W2151340488 @default.
- W2780123820 hasRelatedWork W2168133894 @default.
- W2780123820 hasRelatedWork W2895133117 @default.
- W2780123820 hasRelatedWork W2967129319 @default.
- W2780123820 hasRelatedWork W2995957611 @default.
- W2780123820 hasRelatedWork W3036413187 @default.
- W2780123820 hasRelatedWork W3086019649 @default.
- W2780123820 hasRelatedWork W3091601240 @default.
- W2780123820 hasRelatedWork W3093090008 @default.
- W2780123820 hasRelatedWork W3093959404 @default.
- W2780123820 hasRelatedWork W3136675092 @default.
- W2780123820 hasRelatedWork W3175819369 @default.
- W2780123820 hasRelatedWork W3205801758 @default.
- W2780123820 isParatext "false" @default.
- W2780123820 isRetracted "false" @default.
- W2780123820 magId "2780123820" @default.
- W2780123820 workType "article" @default.