Matches in SemOpenAlex for { <https://semopenalex.org/work/W4313444063> ?p ?o ?g. }
Showing items 1 to 84 of
84
with 100 items per page.
- W4313444063 endingPage "173" @default.
- W4313444063 startingPage "158" @default.
- W4313444063 abstract "Physics simulators have shown great promise for conveniently learning reinforcement learning policies in safe, unconstrained environments. However, transferring the acquired knowledge to the real world can be challenging due to the reality gap. To this end, several methods have been recently proposed to automatically tune simulator parameters with posterior distributions given real data, for use with domain randomization at training time. These approaches have been shown to work for various robotic tasks under different settings and assumptions. Nevertheless, existing literature lacks a thorough comparison of existing adaptive domain randomization methods with respect to transfer performance and real-data efficiency. This work presents an open benchmark for both offline and online methods (SimOpt, BayRn, DROID, DROPO), to investigate current limitations on multiple settings and tasks. We found that online methods are limited by the quality of the currently learned policy for the next iteration, while offline methods may sometimes fail when replaying trajectories in simulation with open-loop commands. The code used is publicly available at https://github.com/gabrieletiboni/adr-benchmark ." @default.
- W4313444063 created "2023-01-06" @default.
- W4313444063 creator A5003059336 @default.
- W4313444063 creator A5004857169 @default.
- W4313444063 creator A5009476175 @default.
- W4313444063 creator A5050576327 @default.
- W4313444063 creator A5080940147 @default.
- W4313444063 date "2023-01-01" @default.
- W4313444063 modified "2023-10-18" @default.
- W4313444063 title "Online vs. Offline Adaptive Domain Randomization Benchmark" @default.
- W4313444063 cites W1977655452 @default.
- W4313444063 cites W2605102758 @default.
- W4313444063 cites W2960705509 @default.
- W4313444063 cites W2962957005 @default.
- W4313444063 cites W2963184939 @default.
- W4313444063 cites W2963906246 @default.
- W4313444063 cites W2968116426 @default.
- W4313444063 cites W3101442004 @default.
- W4313444063 cites W3120778962 @default.
- W4313444063 cites W3126300335 @default.
- W4313444063 cites W3133866887 @default.
- W4313444063 cites W3134153520 @default.
- W4313444063 cites W3183526037 @default.
- W4313444063 cites W3212380917 @default.
- W4313444063 doi "https://doi.org/10.1007/978-3-031-22731-8_12" @default.
- W4313444063 hasPublicationYear "2023" @default.
- W4313444063 type Work @default.
- W4313444063 citedByCount "0" @default.
- W4313444063 crossrefType "book-chapter" @default.
- W4313444063 hasAuthorship W4313444063A5003059336 @default.
- W4313444063 hasAuthorship W4313444063A5004857169 @default.
- W4313444063 hasAuthorship W4313444063A5009476175 @default.
- W4313444063 hasAuthorship W4313444063A5050576327 @default.
- W4313444063 hasAuthorship W4313444063A5080940147 @default.
- W4313444063 hasBestOaLocation W43134440632 @default.
- W4313444063 hasConcept C111919701 @default.
- W4313444063 hasConcept C119857082 @default.
- W4313444063 hasConcept C13280743 @default.
- W4313444063 hasConcept C134306372 @default.
- W4313444063 hasConcept C154945302 @default.
- W4313444063 hasConcept C177264268 @default.
- W4313444063 hasConcept C185798385 @default.
- W4313444063 hasConcept C199360897 @default.
- W4313444063 hasConcept C205649164 @default.
- W4313444063 hasConcept C2776760102 @default.
- W4313444063 hasConcept C2780102126 @default.
- W4313444063 hasConcept C33923547 @default.
- W4313444063 hasConcept C36503486 @default.
- W4313444063 hasConcept C41008148 @default.
- W4313444063 hasConcept C97541855 @default.
- W4313444063 hasConceptScore W4313444063C111919701 @default.
- W4313444063 hasConceptScore W4313444063C119857082 @default.
- W4313444063 hasConceptScore W4313444063C13280743 @default.
- W4313444063 hasConceptScore W4313444063C134306372 @default.
- W4313444063 hasConceptScore W4313444063C154945302 @default.
- W4313444063 hasConceptScore W4313444063C177264268 @default.
- W4313444063 hasConceptScore W4313444063C185798385 @default.
- W4313444063 hasConceptScore W4313444063C199360897 @default.
- W4313444063 hasConceptScore W4313444063C205649164 @default.
- W4313444063 hasConceptScore W4313444063C2776760102 @default.
- W4313444063 hasConceptScore W4313444063C2780102126 @default.
- W4313444063 hasConceptScore W4313444063C33923547 @default.
- W4313444063 hasConceptScore W4313444063C36503486 @default.
- W4313444063 hasConceptScore W4313444063C41008148 @default.
- W4313444063 hasConceptScore W4313444063C97541855 @default.
- W4313444063 hasLocation W43134440631 @default.
- W4313444063 hasLocation W43134440632 @default.
- W4313444063 hasOpenAccess W4313444063 @default.
- W4313444063 hasPrimaryLocation W43134440631 @default.
- W4313444063 hasRelatedWork W2904398858 @default.
- W4313444063 hasRelatedWork W3016525976 @default.
- W4313444063 hasRelatedWork W3128328080 @default.
- W4313444063 hasRelatedWork W3153007185 @default.
- W4313444063 hasRelatedWork W3212439828 @default.
- W4313444063 hasRelatedWork W4225619808 @default.
- W4313444063 hasRelatedWork W4287327031 @default.
- W4313444063 hasRelatedWork W4296474751 @default.
- W4313444063 hasRelatedWork W4303494752 @default.
- W4313444063 hasRelatedWork W4319083788 @default.
- W4313444063 isParatext "false" @default.
- W4313444063 isRetracted "false" @default.
- W4313444063 workType "book-chapter" @default.