FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W2741122588> ?p ?o ?g. }

• W2741122588 abstract "We propose a general and model-free approach for Reinforcement Learning (RL) on real robotics with sparse rewards. We build upon the Deep Deterministic Policy Gradient (DDPG) algorithm to use demonstrations. Both demonstrations and actual interactions are used to fill a replay buffer and the sampling ratio between demonstrations and transitions is automatically tuned via a prioritized replay mechanism. Typically, carefully engineered shaping rewards are required to enable the agents to efficiently explore on high dimensional control problems such as robotics. They are also required for model-based acceleration methods relying on local solvers such as iLQG (e.g. Guided Policy Search and Normalized Advantage Function). The demonstrations replace the need for carefully engineered rewards, and reduce the exploration problem encountered by classical RL approaches in these domains. Demonstrations are collected by a robot kinesthetically force-controlled by a human demonstrator. Results on four simulated insertion tasks show that DDPG from demonstrations out-performs DDPG, and does not require engineered rewards. Finally, we demonstrate the method on a real robotics task consisting of inserting a clip (flexible object) into a rigid object." @default.
• W2741122588 created "2017-08-08" @default.
• W2741122588 creator A5015856388 @default.
• W2741122588 creator A5039155450 @default.
• W2741122588 creator A5041323275 @default.
• W2741122588 creator A5048229171 @default.
• W2741122588 creator A5051968502 @default.
• W2741122588 creator A5054636066 @default.
• W2741122588 creator A5062951341 @default.
• W2741122588 creator A5065100569 @default.
• W2741122588 creator A5077984643 @default.
• W2741122588 creator A5083980378 @default.
• W2741122588 date "2017-07-27" @default.
• W2741122588 modified "2023-10-01" @default.
• W2741122588 title "Leveraging Demonstrations for Deep Reinforcement Learning on Robotics Problems with Sparse Rewards" @default.
• W2741122588 cites W1515851193 @default.
• W2741122588 cites W1777239053 @default.
• W2741122588 cites W2098774185 @default.
• W2741122588 cites W2102847492 @default.
• W2741122588 cites W2104733512 @default.
• W2741122588 cites W2113023245 @default.
• W2741122588 cites W2116774898 @default.
• W2741122588 cites W2145339207 @default.
• W2741122588 cites W2158782408 @default.
• W2741122588 cites W2167224731 @default.
• W2741122588 cites W2167856595 @default.
• W2741122588 cites W2290104316 @default.
• W2741122588 cites W2434014514 @default.
• W2741122588 cites W2544683879 @default.
• W2741122588 cites W2788862220 @default.
• W2741122588 cites W2949608212 @default.
• W2741122588 cites W2950471160 @default.
• W2741122588 cites W2962957031 @default.
• W2741122588 cites W2963477884 @default.
• W2741122588 cites W2963864421 @default.
• W2741122588 hasPublicationYear "2017" @default.
• W2741122588 type Work @default.
• W2741122588 sameAs 2741122588 @default.
• W2741122588 citedByCount "198" @default.
• W2741122588 countsByYear W27411225882016 @default.
• W2741122588 countsByYear W27411225882017 @default.
• W2741122588 countsByYear W27411225882018 @default.
• W2741122588 countsByYear W27411225882019 @default.
• W2741122588 countsByYear W27411225882020 @default.
• W2741122588 countsByYear W27411225882021 @default.
• W2741122588 countsByYear W27411225882022 @default.
• W2741122588 crossrefType "posted-content" @default.
• W2741122588 hasAuthorship W2741122588A5015856388 @default.
• W2741122588 hasAuthorship W2741122588A5039155450 @default.
• W2741122588 hasAuthorship W2741122588A5041323275 @default.
• W2741122588 hasAuthorship W2741122588A5048229171 @default.
• W2741122588 hasAuthorship W2741122588A5051968502 @default.
• W2741122588 hasAuthorship W2741122588A5054636066 @default.
• W2741122588 hasAuthorship W2741122588A5062951341 @default.
• W2741122588 hasAuthorship W2741122588A5065100569 @default.
• W2741122588 hasAuthorship W2741122588A5077984643 @default.
• W2741122588 hasAuthorship W2741122588A5083980378 @default.
• W2741122588 hasConcept C117896860 @default.
• W2741122588 hasConcept C119857082 @default.
• W2741122588 hasConcept C121332964 @default.
• W2741122588 hasConcept C127413603 @default.
• W2741122588 hasConcept C14036430 @default.
• W2741122588 hasConcept C154945302 @default.
• W2741122588 hasConcept C201995342 @default.
• W2741122588 hasConcept C2780451532 @default.
• W2741122588 hasConcept C2781238097 @default.
• W2741122588 hasConcept C34413123 @default.
• W2741122588 hasConcept C41008148 @default.
• W2741122588 hasConcept C74650414 @default.
• W2741122588 hasConcept C78458016 @default.
• W2741122588 hasConcept C86803240 @default.
• W2741122588 hasConcept C90509273 @default.
• W2741122588 hasConcept C97541855 @default.
• W2741122588 hasConceptScore W2741122588C117896860 @default.
• W2741122588 hasConceptScore W2741122588C119857082 @default.
• W2741122588 hasConceptScore W2741122588C121332964 @default.
• W2741122588 hasConceptScore W2741122588C127413603 @default.
• W2741122588 hasConceptScore W2741122588C14036430 @default.
• W2741122588 hasConceptScore W2741122588C154945302 @default.
• W2741122588 hasConceptScore W2741122588C201995342 @default.
• W2741122588 hasConceptScore W2741122588C2780451532 @default.
• W2741122588 hasConceptScore W2741122588C2781238097 @default.
• W2741122588 hasConceptScore W2741122588C34413123 @default.
• W2741122588 hasConceptScore W2741122588C41008148 @default.
• W2741122588 hasConceptScore W2741122588C74650414 @default.
• W2741122588 hasConceptScore W2741122588C78458016 @default.
• W2741122588 hasConceptScore W2741122588C86803240 @default.
• W2741122588 hasConceptScore W2741122588C90509273 @default.
• W2741122588 hasConceptScore W2741122588C97541855 @default.
• W2741122588 hasLocation W27411225881 @default.
• W2741122588 hasOpenAccess W2741122588 @default.
• W2741122588 hasPrimaryLocation W27411225881 @default.
• W2741122588 hasRelatedWork W1757796397 @default.
• W2741122588 hasRelatedWork W1771410628 @default.
• W2741122588 hasRelatedWork W1999874108 @default.
• W2741122588 hasRelatedWork W2061562262 @default.
• W2741122588 hasRelatedWork W2121863487 @default.
• W2741122588 hasRelatedWork W2145339207 @default.
• W2741122588 hasRelatedWork W2155968351 @default.
• W2741122588 hasRelatedWork W2158782408 @default.

• next