Matches in SemOpenAlex for { <https://semopenalex.org/work/W2893649979> ?p ?o ?g. }
Showing items 1 to 93 of
93
with 100 items per page.
- W2893649979 abstract "Deep Reinforcement Learning (DRL) has become a powerful strategy to solve complex decision making problems based on Deep Neural Networks (DNNs). However, it is highly data demanding, so unfeasible in physical systems for most applications. In this work, we approach an alternative Interactive Machine Learning (IML) strategy for training DNN policies based on human corrective feedback, with a method called Deep COACH (D-COACH). This approach not only takes advantage of the knowledge and insights of human teachers as well as the power of DNNs, but also has no need of a reward function (which sometimes implies the need of external perception for computing rewards). We combine Deep Learning with the COrrective Advice Communicated by Humans (COACH) framework, in which non-expert humans shape policies by correcting the agent's actions during execution. The D-COACH framework has the potential to solve complex problems without much data or time required. Experimental results validated the efficiency of the framework in three different problems (two simulated, one with a real robot), with state spaces of low and high dimensions, showing the capacity to successfully learn policies for continuous action spaces like in the Car Racing and Cart-Pole problems faster than with DRL." @default.
- W2893649979 created "2018-10-05" @default.
- W2893649979 creator A5028010633 @default.
- W2893649979 creator A5032303971 @default.
- W2893649979 creator A5035229829 @default.
- W2893649979 creator A5037797188 @default.
- W2893649979 date "2018-09-30" @default.
- W2893649979 modified "2023-09-29" @default.
- W2893649979 title "Interactive Learning with Corrective Feedback for Policies based on Deep Neural Networks" @default.
- W2893649979 cites W122021961 @default.
- W2893649979 cites W1757796397 @default.
- W2893649979 cites W2150818585 @default.
- W2893649979 cites W2156869222 @default.
- W2893649979 cites W2575705757 @default.
- W2893649979 cites W2602717673 @default.
- W2893649979 cites W2626804490 @default.
- W2893649979 cites W2737347195 @default.
- W2893649979 cites W2760057500 @default.
- W2893649979 cites W2799745602 @default.
- W2893649979 cites W2963864421 @default.
- W2893649979 hasPublicationYear "2018" @default.
- W2893649979 type Work @default.
- W2893649979 sameAs 2893649979 @default.
- W2893649979 citedByCount "2" @default.
- W2893649979 countsByYear W28936499792020 @default.
- W2893649979 crossrefType "posted-content" @default.
- W2893649979 hasAuthorship W2893649979A5028010633 @default.
- W2893649979 hasAuthorship W2893649979A5032303971 @default.
- W2893649979 hasAuthorship W2893649979A5035229829 @default.
- W2893649979 hasAuthorship W2893649979A5037797188 @default.
- W2893649979 hasConcept C108583219 @default.
- W2893649979 hasConcept C119857082 @default.
- W2893649979 hasConcept C121332964 @default.
- W2893649979 hasConcept C14036430 @default.
- W2893649979 hasConcept C145420912 @default.
- W2893649979 hasConcept C154945302 @default.
- W2893649979 hasConcept C169760540 @default.
- W2893649979 hasConcept C26760741 @default.
- W2893649979 hasConcept C2779305910 @default.
- W2893649979 hasConcept C2780791683 @default.
- W2893649979 hasConcept C2984842247 @default.
- W2893649979 hasConcept C33923547 @default.
- W2893649979 hasConcept C41008148 @default.
- W2893649979 hasConcept C50644808 @default.
- W2893649979 hasConcept C62520636 @default.
- W2893649979 hasConcept C78458016 @default.
- W2893649979 hasConcept C86803240 @default.
- W2893649979 hasConcept C97541855 @default.
- W2893649979 hasConceptScore W2893649979C108583219 @default.
- W2893649979 hasConceptScore W2893649979C119857082 @default.
- W2893649979 hasConceptScore W2893649979C121332964 @default.
- W2893649979 hasConceptScore W2893649979C14036430 @default.
- W2893649979 hasConceptScore W2893649979C145420912 @default.
- W2893649979 hasConceptScore W2893649979C154945302 @default.
- W2893649979 hasConceptScore W2893649979C169760540 @default.
- W2893649979 hasConceptScore W2893649979C26760741 @default.
- W2893649979 hasConceptScore W2893649979C2779305910 @default.
- W2893649979 hasConceptScore W2893649979C2780791683 @default.
- W2893649979 hasConceptScore W2893649979C2984842247 @default.
- W2893649979 hasConceptScore W2893649979C33923547 @default.
- W2893649979 hasConceptScore W2893649979C41008148 @default.
- W2893649979 hasConceptScore W2893649979C50644808 @default.
- W2893649979 hasConceptScore W2893649979C62520636 @default.
- W2893649979 hasConceptScore W2893649979C78458016 @default.
- W2893649979 hasConceptScore W2893649979C86803240 @default.
- W2893649979 hasConceptScore W2893649979C97541855 @default.
- W2893649979 hasLocation W28936499791 @default.
- W2893649979 hasOpenAccess W2893649979 @default.
- W2893649979 hasPrimaryLocation W28936499791 @default.
- W2893649979 hasRelatedWork W1595483645 @default.
- W2893649979 hasRelatedWork W2513373085 @default.
- W2893649979 hasRelatedWork W2528734395 @default.
- W2893649979 hasRelatedWork W2765397130 @default.
- W2893649979 hasRelatedWork W2790924949 @default.
- W2893649979 hasRelatedWork W2911719076 @default.
- W2893649979 hasRelatedWork W2951561730 @default.
- W2893649979 hasRelatedWork W2963293747 @default.
- W2893649979 hasRelatedWork W2964161785 @default.
- W2893649979 hasRelatedWork W2964263543 @default.
- W2893649979 hasRelatedWork W2969011875 @default.
- W2893649979 hasRelatedWork W2997970896 @default.
- W2893649979 hasRelatedWork W2999490157 @default.
- W2893649979 hasRelatedWork W3002128304 @default.
- W2893649979 hasRelatedWork W3005607450 @default.
- W2893649979 hasRelatedWork W3090876870 @default.
- W2893649979 hasRelatedWork W3109409708 @default.
- W2893649979 hasRelatedWork W3151079898 @default.
- W2893649979 hasRelatedWork W3167658443 @default.
- W2893649979 hasRelatedWork W3203056473 @default.
- W2893649979 isParatext "false" @default.
- W2893649979 isRetracted "false" @default.
- W2893649979 magId "2893649979" @default.
- W2893649979 workType "article" @default.