FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W2890822044> ?p ?o ?g. }

• W2890822044 abstract "GAIL is a recent successful imitation learning architecture that exploits the adversarial training procedure introduced in GANs. Albeit successful at generating behaviours similar to those demonstrated to the agent, GAIL suffers from a high sample complexity in the number of interactions it has to carry out in the environment in order to achieve satisfactory performance. We dramatically shrink the amount of interactions with the environment necessary to learn well-behaved imitation policies, by up to several orders of magnitude. Our framework, operating in the model-free regime, exhibits a significant increase in sample-efficiency over previous methods by simultaneously a) learning a self-tuned adversarially-trained surrogate reward and b) leveraging an off-policy actor-critic architecture. We show that our approach is simple to implement and that the learned agents remain remarkably stable, as shown in our experiments that span a variety of continuous control tasks. Video visualisations available at: url{this https URL}." @default.
• W2890822044 created "2018-09-27" @default.
• W2890822044 creator A5039285242 @default.
• W2890822044 creator A5084831490 @default.
• W2890822044 date "2018-09-06" @default.
• W2890822044 modified "2023-09-27" @default.
• W2890822044 title "Sample-Efficient Imitation Learning via Generative Adversarial Nets" @default.
• W2890822044 cites W1522301498 @default.
• W2890822044 cites W1684361744 @default.
• W2890822044 cites W1737105075 @default.
• W2890822044 cites W1757796397 @default.
• W2890822044 cites W1771410628 @default.
• W2890822044 cites W1777239053 @default.
• W2890822044 cites W1999874108 @default.
• W2890822044 cites W2099471712 @default.
• W2890822044 cites W2102847492 @default.
• W2890822044 cites W2113023245 @default.
• W2890822044 cites W2117109997 @default.
• W2890822044 cites W2117675763 @default.
• W2890822044 cites W2121863487 @default.
• W2890822044 cites W2142641780 @default.
• W2890822044 cites W2145339207 @default.
• W2890822044 cites W2155027007 @default.
• W2890822044 cites W2158782408 @default.
• W2890822044 cites W2165150801 @default.
• W2890822044 cites W2167224731 @default.
• W2890822044 cites W2401592218 @default.
• W2890822044 cites W2509374375 @default.
• W2890822044 cites W2527819024 @default.
• W2890822044 cites W2547875792 @default.
• W2890822044 cites W2548228487 @default.
• W2890822044 cites W2554984891 @default.
• W2890822044 cites W2556958149 @default.
• W2890822044 cites W2566467060 @default.
• W2890822044 cites W2724169821 @default.
• W2890822044 cites W2736601468 @default.
• W2890822044 cites W2740210681 @default.
• W2890822044 cites W2741122588 @default.
• W2890822044 cites W2754517384 @default.
• W2890822044 cites W2761873684 @default.
• W2890822044 cites W2765658450 @default.
• W2890822044 cites W2766290211 @default.
• W2890822044 cites W2768599997 @default.
• W2890822044 cites W2785635021 @default.
• W2890822044 cites W2899041500 @default.
• W2890822044 cites W2949608212 @default.
• W2890822044 cites W2951004968 @default.
• W2890822044 cites W2962879692 @default.
• W2890822044 cites W2962957031 @default.
• W2890822044 cites W2963024489 @default.
• W2890822044 cites W2963221965 @default.
• W2890822044 cites W2963277051 @default.
• W2890822044 cites W2963328631 @default.
• W2890822044 cites W2963477884 @default.
• W2890822044 cites W2963508354 @default.
• W2890822044 cites W2963864421 @default.
• W2890822044 cites W2964201867 @default.
• W2890822044 cites W2971482891 @default.
• W2890822044 cites W3037207827 @default.
• W2890822044 cites W3037932933 @default.
• W2890822044 hasPublicationYear "2018" @default.
• W2890822044 type Work @default.
• W2890822044 sameAs 2890822044 @default.
• W2890822044 citedByCount "2" @default.
• W2890822044 countsByYear W28908220442019 @default.
• W2890822044 crossrefType "posted-content" @default.
• W2890822044 hasAuthorship W2890822044A5039285242 @default.
• W2890822044 hasAuthorship W2890822044A5084831490 @default.
• W2890822044 hasConcept C119857082 @default.
• W2890822044 hasConcept C123657996 @default.
• W2890822044 hasConcept C126388530 @default.
• W2890822044 hasConcept C136197465 @default.
• W2890822044 hasConcept C142362112 @default.
• W2890822044 hasConcept C153349607 @default.
• W2890822044 hasConcept C154945302 @default.
• W2890822044 hasConcept C15744967 @default.
• W2890822044 hasConcept C165696696 @default.
• W2890822044 hasConcept C185592680 @default.
• W2890822044 hasConcept C198531522 @default.
• W2890822044 hasConcept C2775924081 @default.
• W2890822044 hasConcept C2778445095 @default.
• W2890822044 hasConcept C37736160 @default.
• W2890822044 hasConcept C38652104 @default.
• W2890822044 hasConcept C39890363 @default.
• W2890822044 hasConcept C41008148 @default.
• W2890822044 hasConcept C43617362 @default.
• W2890822044 hasConcept C77805123 @default.
• W2890822044 hasConcept C97541855 @default.
• W2890822044 hasConceptScore W2890822044C119857082 @default.
• W2890822044 hasConceptScore W2890822044C123657996 @default.
• W2890822044 hasConceptScore W2890822044C126388530 @default.
• W2890822044 hasConceptScore W2890822044C136197465 @default.
• W2890822044 hasConceptScore W2890822044C142362112 @default.
• W2890822044 hasConceptScore W2890822044C153349607 @default.
• W2890822044 hasConceptScore W2890822044C154945302 @default.
• W2890822044 hasConceptScore W2890822044C15744967 @default.
• W2890822044 hasConceptScore W2890822044C165696696 @default.
• W2890822044 hasConceptScore W2890822044C185592680 @default.
• W2890822044 hasConceptScore W2890822044C198531522 @default.
• W2890822044 hasConceptScore W2890822044C2775924081 @default.

• next