Matches in SemOpenAlex for { <https://semopenalex.org/work/W3091489580> ?p ?o ?g. }
- W3091489580 abstract "The goal of this paper is to present a method for simultaneous trajectory and local stabilizing policy optimization to generate local policies for trajectory-centric model-based reinforcement learning (MBRL). This is motivated by the fact that global policy optimization for non-linear systems could be a very challenging problem both algorithmically and numerically. However, a lot of robotic manipulation tasks are trajectory-centric, and thus do not require a global model or policy. Due to inaccuracies in the learned model estimates, an open-loop trajectory optimization process mostly results in very poor performance when used on the real system. Motivated by these problems, we try to formulate the problem of trajectory optimization and local policy synthesis as a single optimization problem. It is then solved simultaneously as an instance of nonlinear programming. We provide some results for analysis as well as achieved performance of the proposed technique under some simplifying assumptions." @default.
- W3091489580 created "2020-10-08" @default.
- W3091489580 creator A5010530960 @default.
- W3091489580 creator A5016137188 @default.
- W3091489580 creator A5038062267 @default.
- W3091489580 creator A5053957972 @default.
- W3091489580 creator A5054931604 @default.
- W3091489580 creator A5062272788 @default.
- W3091489580 creator A5065878109 @default.
- W3091489580 date "2020-05-01" @default.
- W3091489580 modified "2023-09-30" @default.
- W3091489580 title "Local Policy Optimization for Trajectory-Centric Reinforcement Learning" @default.
- W3091489580 cites W1502922572 @default.
- W3091489580 cites W1543439990 @default.
- W3091489580 cites W1742307920 @default.
- W3091489580 cites W1925816294 @default.
- W3091489580 cites W2046210054 @default.
- W3091489580 cites W2087617385 @default.
- W3091489580 cites W2100538121 @default.
- W3091489580 cites W2104733512 @default.
- W3091489580 cites W2121863487 @default.
- W3091489580 cites W2140135625 @default.
- W3091489580 cites W2148247550 @default.
- W3091489580 cites W2164278908 @default.
- W3091489580 cites W2257979135 @default.
- W3091489580 cites W2529601334 @default.
- W3091489580 cites W2738778707 @default.
- W3091489580 cites W2766447205 @default.
- W3091489580 cites W2786936262 @default.
- W3091489580 cites W2798766386 @default.
- W3091489580 cites W2953708620 @default.
- W3091489580 cites W2962872206 @default.
- W3091489580 cites W2963630259 @default.
- W3091489580 cites W2964161785 @default.
- W3091489580 cites W2967651253 @default.
- W3091489580 cites W2969101033 @default.
- W3091489580 cites W2972785326 @default.
- W3091489580 cites W2974750625 @default.
- W3091489580 cites W3011457441 @default.
- W3091489580 doi "https://doi.org/10.1109/icra40945.2020.9197058" @default.
- W3091489580 hasPublicationYear "2020" @default.
- W3091489580 type Work @default.
- W3091489580 sameAs 3091489580 @default.
- W3091489580 citedByCount "4" @default.
- W3091489580 countsByYear W30914895802021 @default.
- W3091489580 countsByYear W30914895802022 @default.
- W3091489580 crossrefType "proceedings-article" @default.
- W3091489580 hasAuthorship W3091489580A5010530960 @default.
- W3091489580 hasAuthorship W3091489580A5016137188 @default.
- W3091489580 hasAuthorship W3091489580A5038062267 @default.
- W3091489580 hasAuthorship W3091489580A5053957972 @default.
- W3091489580 hasAuthorship W3091489580A5054931604 @default.
- W3091489580 hasAuthorship W3091489580A5062272788 @default.
- W3091489580 hasAuthorship W3091489580A5065878109 @default.
- W3091489580 hasBestOaLocation W30914895802 @default.
- W3091489580 hasConcept C111919701 @default.
- W3091489580 hasConcept C11413529 @default.
- W3091489580 hasConcept C115527620 @default.
- W3091489580 hasConcept C121332964 @default.
- W3091489580 hasConcept C126255220 @default.
- W3091489580 hasConcept C1276947 @default.
- W3091489580 hasConcept C13662910 @default.
- W3091489580 hasConcept C137836250 @default.
- W3091489580 hasConcept C141934464 @default.
- W3091489580 hasConcept C154945302 @default.
- W3091489580 hasConcept C158622935 @default.
- W3091489580 hasConcept C164752517 @default.
- W3091489580 hasConcept C173246807 @default.
- W3091489580 hasConcept C33923547 @default.
- W3091489580 hasConcept C41008148 @default.
- W3091489580 hasConcept C62520636 @default.
- W3091489580 hasConcept C91575142 @default.
- W3091489580 hasConcept C97541855 @default.
- W3091489580 hasConcept C98045186 @default.
- W3091489580 hasConceptScore W3091489580C111919701 @default.
- W3091489580 hasConceptScore W3091489580C11413529 @default.
- W3091489580 hasConceptScore W3091489580C115527620 @default.
- W3091489580 hasConceptScore W3091489580C121332964 @default.
- W3091489580 hasConceptScore W3091489580C126255220 @default.
- W3091489580 hasConceptScore W3091489580C1276947 @default.
- W3091489580 hasConceptScore W3091489580C13662910 @default.
- W3091489580 hasConceptScore W3091489580C137836250 @default.
- W3091489580 hasConceptScore W3091489580C141934464 @default.
- W3091489580 hasConceptScore W3091489580C154945302 @default.
- W3091489580 hasConceptScore W3091489580C158622935 @default.
- W3091489580 hasConceptScore W3091489580C164752517 @default.
- W3091489580 hasConceptScore W3091489580C173246807 @default.
- W3091489580 hasConceptScore W3091489580C33923547 @default.
- W3091489580 hasConceptScore W3091489580C41008148 @default.
- W3091489580 hasConceptScore W3091489580C62520636 @default.
- W3091489580 hasConceptScore W3091489580C91575142 @default.
- W3091489580 hasConceptScore W3091489580C97541855 @default.
- W3091489580 hasConceptScore W3091489580C98045186 @default.
- W3091489580 hasLocation W30914895801 @default.
- W3091489580 hasLocation W30914895802 @default.
- W3091489580 hasOpenAccess W3091489580 @default.
- W3091489580 hasPrimaryLocation W30914895801 @default.
- W3091489580 hasRelatedWork W1279312 @default.
- W3091489580 hasRelatedWork W1290750 @default.
- W3091489580 hasRelatedWork W1311792 @default.