Matches in SemOpenAlex for { <https://semopenalex.org/work/W2765720089> ?p ?o ?g. }
Showing items 1 to 81 of
81
with 100 items per page.
- W2765720089 abstract "The technique called ‘Coaching’ is proposed in this work. Coaching is a method to accelerate learning by employing a human knowledge at the early phase of learning. The human coach can guide a robot behavior by temporarily replacing the global goal with an intermediate target. During the coaching process, an action is chosen by a greedy policy such that it is most likely driving the robot to the intermediate target. When the intermediate target is reached, a normal pair of policy (f-greedy) and reward function is switched back. However, the global reward function is still used for updating the state-action value during both coaching and non-coaching periods. A human coach can guide the robot by using 8 verbal commands to place the intermediate target location relative to the agent current location. In this work, Q learning algorithm was used to test with the proposed method on 2 learning tasks: ball following, and obstacle avoidance. The proposed technique resulted in faster learning performance when compared to the traditional method of reinforcement learning." @default.
- W2765720089 created "2017-11-10" @default.
- W2765720089 creator A5007850277 @default.
- W2765720089 creator A5020688973 @default.
- W2765720089 date "2017-08-01" @default.
- W2765720089 modified "2023-09-25" @default.
- W2765720089 title "Coaching: Human-assisted approach for reinforcement learning" @default.
- W2765720089 cites W121023703 @default.
- W2765720089 cites W1536323281 @default.
- W2765720089 cites W2103285838 @default.
- W2765720089 cites W2116157560 @default.
- W2765720089 cites W2121110499 @default.
- W2765720089 cites W2121863487 @default.
- W2765720089 cites W2156869222 @default.
- W2765720089 cites W2294422333 @default.
- W2765720089 cites W2947873954 @default.
- W2765720089 cites W82514683 @default.
- W2765720089 doi "https://doi.org/10.1109/icras.2017.8071940" @default.
- W2765720089 hasPublicationYear "2017" @default.
- W2765720089 type Work @default.
- W2765720089 sameAs 2765720089 @default.
- W2765720089 citedByCount "1" @default.
- W2765720089 countsByYear W27657200892021 @default.
- W2765720089 crossrefType "proceedings-article" @default.
- W2765720089 hasAuthorship W2765720089A5007850277 @default.
- W2765720089 hasAuthorship W2765720089A5020688973 @default.
- W2765720089 hasConcept C121332964 @default.
- W2765720089 hasConcept C154945302 @default.
- W2765720089 hasConcept C15744967 @default.
- W2765720089 hasConcept C17744445 @default.
- W2765720089 hasConcept C188116033 @default.
- W2765720089 hasConcept C199539241 @default.
- W2765720089 hasConcept C2776650193 @default.
- W2765720089 hasConcept C2779363792 @default.
- W2765720089 hasConcept C2780791683 @default.
- W2765720089 hasConcept C41008148 @default.
- W2765720089 hasConcept C542102704 @default.
- W2765720089 hasConcept C62520636 @default.
- W2765720089 hasConcept C90509273 @default.
- W2765720089 hasConcept C97541855 @default.
- W2765720089 hasConceptScore W2765720089C121332964 @default.
- W2765720089 hasConceptScore W2765720089C154945302 @default.
- W2765720089 hasConceptScore W2765720089C15744967 @default.
- W2765720089 hasConceptScore W2765720089C17744445 @default.
- W2765720089 hasConceptScore W2765720089C188116033 @default.
- W2765720089 hasConceptScore W2765720089C199539241 @default.
- W2765720089 hasConceptScore W2765720089C2776650193 @default.
- W2765720089 hasConceptScore W2765720089C2779363792 @default.
- W2765720089 hasConceptScore W2765720089C2780791683 @default.
- W2765720089 hasConceptScore W2765720089C41008148 @default.
- W2765720089 hasConceptScore W2765720089C542102704 @default.
- W2765720089 hasConceptScore W2765720089C62520636 @default.
- W2765720089 hasConceptScore W2765720089C90509273 @default.
- W2765720089 hasConceptScore W2765720089C97541855 @default.
- W2765720089 hasLocation W27657200891 @default.
- W2765720089 hasOpenAccess W2765720089 @default.
- W2765720089 hasPrimaryLocation W27657200891 @default.
- W2765720089 hasRelatedWork W13926559 @default.
- W2765720089 hasRelatedWork W1457482454 @default.
- W2765720089 hasRelatedWork W1487478277 @default.
- W2765720089 hasRelatedWork W1585546346 @default.
- W2765720089 hasRelatedWork W1882507001 @default.
- W2765720089 hasRelatedWork W2101761545 @default.
- W2765720089 hasRelatedWork W2129659607 @default.
- W2765720089 hasRelatedWork W2149645818 @default.
- W2765720089 hasRelatedWork W2365393372 @default.
- W2765720089 hasRelatedWork W2381730280 @default.
- W2765720089 hasRelatedWork W2397582123 @default.
- W2765720089 hasRelatedWork W2410462364 @default.
- W2765720089 hasRelatedWork W2515948165 @default.
- W2765720089 hasRelatedWork W2615565422 @default.
- W2765720089 hasRelatedWork W2808546214 @default.
- W2765720089 hasRelatedWork W2942980725 @default.
- W2765720089 hasRelatedWork W3174851555 @default.
- W2765720089 hasRelatedWork W1488823363 @default.
- W2765720089 hasRelatedWork W2102483743 @default.
- W2765720089 hasRelatedWork W303692054 @default.
- W2765720089 isParatext "false" @default.
- W2765720089 isRetracted "false" @default.
- W2765720089 magId "2765720089" @default.
- W2765720089 workType "article" @default.