Matches in SemOpenAlex for { <https://semopenalex.org/work/W2968805005> ?p ?o ?g. }
Showing items 1 to 80 of
80
with 100 items per page.
- W2968805005 abstract "The design of reward functions in reinforcement learning is a human skill that comes with experience. Unfortunately, there is not any methodology in the literature that could guide a human to design the reward function or to allow a human to transfer the skills developed in designing reward functions to another human and in a systematic manner. In this paper, we use Systematic Instructional Design, an approach in human education, to engineer a machine education methodology to design reward functions for reinforcement learning. We demonstrate the methodology in designing a hierarchical genetic reinforcement learner that adopts a neural network representation to evolve a swarm controller for an agent shepherding a boids-based swarm. The results reveal that the methodology is able to guide the design of hierarchical reinforcement learners, with each model in the hierarchy learning incrementally through a multi-part reward function. The hierarchy acts as a decision fusion function that combines the individual behaviours and skills learnt by each instruction to create a smart shepherd to control the swarm." @default.
- W2968805005 created "2019-08-22" @default.
- W2968805005 creator A5022974795 @default.
- W2968805005 creator A5025807780 @default.
- W2968805005 date "2019-06-01" @default.
- W2968805005 modified "2023-10-01" @default.
- W2968805005 title "Machine Teaching in Hierarchical Genetic Reinforcement Learning: Curriculum Design of Reward Functions for Swarm Shepherding" @default.
- W2968805005 cites W1974014372 @default.
- W2968805005 cites W2001773175 @default.
- W2968805005 cites W2049287437 @default.
- W2968805005 cites W2119120935 @default.
- W2968805005 cites W2134493171 @default.
- W2968805005 cites W2150312211 @default.
- W2968805005 cites W2161205534 @default.
- W2968805005 cites W2170591991 @default.
- W2968805005 cites W2400329691 @default.
- W2968805005 cites W2491785880 @default.
- W2968805005 cites W2587233709 @default.
- W2968805005 cites W2769558701 @default.
- W2968805005 cites W2782946658 @default.
- W2968805005 cites W2900835512 @default.
- W2968805005 cites W4213113494 @default.
- W2968805005 cites W4249373955 @default.
- W2968805005 doi "https://doi.org/10.1109/cec.2019.8790157" @default.
- W2968805005 hasPublicationYear "2019" @default.
- W2968805005 type Work @default.
- W2968805005 sameAs 2968805005 @default.
- W2968805005 citedByCount "12" @default.
- W2968805005 countsByYear W29688050052019 @default.
- W2968805005 countsByYear W29688050052020 @default.
- W2968805005 countsByYear W29688050052021 @default.
- W2968805005 countsByYear W29688050052023 @default.
- W2968805005 crossrefType "proceedings-article" @default.
- W2968805005 hasAuthorship W2968805005A5022974795 @default.
- W2968805005 hasAuthorship W2968805005A5025807780 @default.
- W2968805005 hasBestOaLocation W29688050052 @default.
- W2968805005 hasConcept C107457646 @default.
- W2968805005 hasConcept C119857082 @default.
- W2968805005 hasConcept C14036430 @default.
- W2968805005 hasConcept C154945302 @default.
- W2968805005 hasConcept C162324750 @default.
- W2968805005 hasConcept C181335050 @default.
- W2968805005 hasConcept C31170391 @default.
- W2968805005 hasConcept C34447519 @default.
- W2968805005 hasConcept C41008148 @default.
- W2968805005 hasConcept C50644808 @default.
- W2968805005 hasConcept C78458016 @default.
- W2968805005 hasConcept C86803240 @default.
- W2968805005 hasConcept C97541855 @default.
- W2968805005 hasConceptScore W2968805005C107457646 @default.
- W2968805005 hasConceptScore W2968805005C119857082 @default.
- W2968805005 hasConceptScore W2968805005C14036430 @default.
- W2968805005 hasConceptScore W2968805005C154945302 @default.
- W2968805005 hasConceptScore W2968805005C162324750 @default.
- W2968805005 hasConceptScore W2968805005C181335050 @default.
- W2968805005 hasConceptScore W2968805005C31170391 @default.
- W2968805005 hasConceptScore W2968805005C34447519 @default.
- W2968805005 hasConceptScore W2968805005C41008148 @default.
- W2968805005 hasConceptScore W2968805005C50644808 @default.
- W2968805005 hasConceptScore W2968805005C78458016 @default.
- W2968805005 hasConceptScore W2968805005C86803240 @default.
- W2968805005 hasConceptScore W2968805005C97541855 @default.
- W2968805005 hasLocation W29688050051 @default.
- W2968805005 hasLocation W29688050052 @default.
- W2968805005 hasOpenAccess W2968805005 @default.
- W2968805005 hasPrimaryLocation W29688050051 @default.
- W2968805005 hasRelatedWork W260766989 @default.
- W2968805005 hasRelatedWork W2959276766 @default.
- W2968805005 hasRelatedWork W2961085424 @default.
- W2968805005 hasRelatedWork W2976657239 @default.
- W2968805005 hasRelatedWork W3074294383 @default.
- W2968805005 hasRelatedWork W3139193008 @default.
- W2968805005 hasRelatedWork W4206669594 @default.
- W2968805005 hasRelatedWork W4295941380 @default.
- W2968805005 hasRelatedWork W4319083788 @default.
- W2968805005 hasRelatedWork W4320059794 @default.
- W2968805005 isParatext "false" @default.
- W2968805005 isRetracted "false" @default.
- W2968805005 magId "2968805005" @default.
- W2968805005 workType "article" @default.