Matches in SemOpenAlex for { <https://semopenalex.org/work/W2765175013> ?p ?o ?g. }
- W2765175013 abstract "Understanding physical phenomena is a key component of human intelligence and enables physical interaction with previously unseen environments. In this paper, we study how an artificial agent can autonomously acquire this intuition through interaction with the environment. We created a synthetic block stacking environment with physics simulation in which the agent can learn a policy end-to-end through trial and error. Thereby, we bypass to explicitly model physical knowledge within the policy. We are specifically interested in tasks that require the agent to reach a given goal state that may be different for every new trial. To this end, we propose a deep reinforcement learning framework that learns policies which are parametrized by a goal. We validated the model on a toy example navigating in a grid world with different target positions and in a block stacking task with different target structures of the final tower. In contrast to prior work, our policies show better generalization across different goals." @default.
- W2765175013 created "2017-11-10" @default.
- W2765175013 creator A5003887059 @default.
- W2765175013 creator A5021676288 @default.
- W2765175013 creator A5091798976 @default.
- W2765175013 date "2017-11-01" @default.
- W2765175013 modified "2023-09-24" @default.
- W2765175013 title "Acquiring Target Stacking Skills by Goal-Parameterized Deep Reinforcement Learning" @default.
- W2765175013 cites W1512866498 @default.
- W2765175013 cites W1531117899 @default.
- W2765175013 cites W1757796397 @default.
- W2765175013 cites W1777239053 @default.
- W2765175013 cites W2024915064 @default.
- W2765175013 cites W2036096913 @default.
- W2765175013 cites W2059100041 @default.
- W2765175013 cites W2145339207 @default.
- W2765175013 cites W2156256170 @default.
- W2765175013 cites W2181623680 @default.
- W2765175013 cites W2257000838 @default.
- W2765175013 cites W2271155703 @default.
- W2765175013 cites W2312995908 @default.
- W2765175013 cites W2473208550 @default.
- W2765175013 cites W2553347458 @default.
- W2765175013 cites W2572772963 @default.
- W2765175013 cites W2586029550 @default.
- W2765175013 cites W2737660050 @default.
- W2765175013 cites W2951384764 @default.
- W2765175013 cites W2951942526 @default.
- W2765175013 cites W567721252 @default.
- W2765175013 hasPublicationYear "2017" @default.
- W2765175013 type Work @default.
- W2765175013 sameAs 2765175013 @default.
- W2765175013 citedByCount "2" @default.
- W2765175013 countsByYear W27651750132018 @default.
- W2765175013 countsByYear W27651750132019 @default.
- W2765175013 crossrefType "posted-content" @default.
- W2765175013 hasAuthorship W2765175013A5003887059 @default.
- W2765175013 hasAuthorship W2765175013A5021676288 @default.
- W2765175013 hasAuthorship W2765175013A5091798976 @default.
- W2765175013 hasConcept C107457646 @default.
- W2765175013 hasConcept C11413529 @default.
- W2765175013 hasConcept C119857082 @default.
- W2765175013 hasConcept C121332964 @default.
- W2765175013 hasConcept C127413603 @default.
- W2765175013 hasConcept C132010649 @default.
- W2765175013 hasConcept C134306372 @default.
- W2765175013 hasConcept C154945302 @default.
- W2765175013 hasConcept C15744967 @default.
- W2765175013 hasConcept C165464430 @default.
- W2765175013 hasConcept C177148314 @default.
- W2765175013 hasConcept C187691185 @default.
- W2765175013 hasConcept C188147891 @default.
- W2765175013 hasConcept C201995342 @default.
- W2765175013 hasConcept C2524010 @default.
- W2765175013 hasConcept C2777210771 @default.
- W2765175013 hasConcept C2780451532 @default.
- W2765175013 hasConcept C33347731 @default.
- W2765175013 hasConcept C33923547 @default.
- W2765175013 hasConcept C41008148 @default.
- W2765175013 hasConcept C46141821 @default.
- W2765175013 hasConcept C77805123 @default.
- W2765175013 hasConcept C84653758 @default.
- W2765175013 hasConcept C97541855 @default.
- W2765175013 hasConceptScore W2765175013C107457646 @default.
- W2765175013 hasConceptScore W2765175013C11413529 @default.
- W2765175013 hasConceptScore W2765175013C119857082 @default.
- W2765175013 hasConceptScore W2765175013C121332964 @default.
- W2765175013 hasConceptScore W2765175013C127413603 @default.
- W2765175013 hasConceptScore W2765175013C132010649 @default.
- W2765175013 hasConceptScore W2765175013C134306372 @default.
- W2765175013 hasConceptScore W2765175013C154945302 @default.
- W2765175013 hasConceptScore W2765175013C15744967 @default.
- W2765175013 hasConceptScore W2765175013C165464430 @default.
- W2765175013 hasConceptScore W2765175013C177148314 @default.
- W2765175013 hasConceptScore W2765175013C187691185 @default.
- W2765175013 hasConceptScore W2765175013C188147891 @default.
- W2765175013 hasConceptScore W2765175013C201995342 @default.
- W2765175013 hasConceptScore W2765175013C2524010 @default.
- W2765175013 hasConceptScore W2765175013C2777210771 @default.
- W2765175013 hasConceptScore W2765175013C2780451532 @default.
- W2765175013 hasConceptScore W2765175013C33347731 @default.
- W2765175013 hasConceptScore W2765175013C33923547 @default.
- W2765175013 hasConceptScore W2765175013C41008148 @default.
- W2765175013 hasConceptScore W2765175013C46141821 @default.
- W2765175013 hasConceptScore W2765175013C77805123 @default.
- W2765175013 hasConceptScore W2765175013C84653758 @default.
- W2765175013 hasConceptScore W2765175013C97541855 @default.
- W2765175013 hasLocation W27651750131 @default.
- W2765175013 hasOpenAccess W2765175013 @default.
- W2765175013 hasPrimaryLocation W27651750131 @default.
- W2765175013 hasRelatedWork W1604959332 @default.
- W2765175013 hasRelatedWork W2020573190 @default.
- W2765175013 hasRelatedWork W2051891848 @default.
- W2765175013 hasRelatedWork W2553701371 @default.
- W2765175013 hasRelatedWork W2756467676 @default.
- W2765175013 hasRelatedWork W2792404612 @default.
- W2765175013 hasRelatedWork W2883869105 @default.
- W2765175013 hasRelatedWork W2883899184 @default.
- W2765175013 hasRelatedWork W2963096144 @default.
- W2765175013 hasRelatedWork W2963619650 @default.