Matches in SemOpenAlex for { <https://semopenalex.org/work/W4288283534> ?p ?o ?g. }
Showing items 1 to 76 of
76
with 100 items per page.
- W4288283534 abstract "In multi-task reinforcement learning there are two main challenges: at training time, the ability to learn different policies with a single model; at test time, inferring which of those policies applying without an external signal. In the case of continual reinforcement learning a third challenge arises: learning tasks sequentially without forgetting the previous ones. In this paper, we tackle these challenges by proposing DisCoRL, an approach combining state representation learning and policy distillation. We experiment on a sequence of three simulated 2D navigation tasks with a 3 wheel omni-directional robot. Moreover, we tested our approach's robustness by transferring the final policy into a real life setting. The policy can solve all tasks and automatically infer which one to run." @default.
- W4288283534 created "2022-07-28" @default.
- W4288283534 creator A5006026661 @default.
- W4288283534 creator A5025408105 @default.
- W4288283534 creator A5040828370 @default.
- W4288283534 creator A5058176171 @default.
- W4288283534 creator A5065902491 @default.
- W4288283534 creator A5067072090 @default.
- W4288283534 creator A5090996230 @default.
- W4288283534 date "2019-12-14" @default.
- W4288283534 modified "2023-09-27" @default.
- W4288283534 title "DISCORL: Continual reinforcement learning via policy distillation" @default.
- W4288283534 hasPublicationYear "2019" @default.
- W4288283534 type Work @default.
- W4288283534 citedByCount "0" @default.
- W4288283534 crossrefType "proceedings-article" @default.
- W4288283534 hasAuthorship W4288283534A5006026661 @default.
- W4288283534 hasAuthorship W4288283534A5025408105 @default.
- W4288283534 hasAuthorship W4288283534A5040828370 @default.
- W4288283534 hasAuthorship W4288283534A5058176171 @default.
- W4288283534 hasAuthorship W4288283534A5065902491 @default.
- W4288283534 hasAuthorship W4288283534A5067072090 @default.
- W4288283534 hasAuthorship W4288283534A5090996230 @default.
- W4288283534 hasBestOaLocation W42882835341 @default.
- W4288283534 hasConcept C104317684 @default.
- W4288283534 hasConcept C119857082 @default.
- W4288283534 hasConcept C127413603 @default.
- W4288283534 hasConcept C138885662 @default.
- W4288283534 hasConcept C154945302 @default.
- W4288283534 hasConcept C178790620 @default.
- W4288283534 hasConcept C185592680 @default.
- W4288283534 hasConcept C201995342 @default.
- W4288283534 hasConcept C204030448 @default.
- W4288283534 hasConcept C2780451532 @default.
- W4288283534 hasConcept C41008148 @default.
- W4288283534 hasConcept C41895202 @default.
- W4288283534 hasConcept C55493867 @default.
- W4288283534 hasConcept C63479239 @default.
- W4288283534 hasConcept C7149132 @default.
- W4288283534 hasConcept C90509273 @default.
- W4288283534 hasConcept C97541855 @default.
- W4288283534 hasConceptScore W4288283534C104317684 @default.
- W4288283534 hasConceptScore W4288283534C119857082 @default.
- W4288283534 hasConceptScore W4288283534C127413603 @default.
- W4288283534 hasConceptScore W4288283534C138885662 @default.
- W4288283534 hasConceptScore W4288283534C154945302 @default.
- W4288283534 hasConceptScore W4288283534C178790620 @default.
- W4288283534 hasConceptScore W4288283534C185592680 @default.
- W4288283534 hasConceptScore W4288283534C201995342 @default.
- W4288283534 hasConceptScore W4288283534C204030448 @default.
- W4288283534 hasConceptScore W4288283534C2780451532 @default.
- W4288283534 hasConceptScore W4288283534C41008148 @default.
- W4288283534 hasConceptScore W4288283534C41895202 @default.
- W4288283534 hasConceptScore W4288283534C55493867 @default.
- W4288283534 hasConceptScore W4288283534C63479239 @default.
- W4288283534 hasConceptScore W4288283534C7149132 @default.
- W4288283534 hasConceptScore W4288283534C90509273 @default.
- W4288283534 hasConceptScore W4288283534C97541855 @default.
- W4288283534 hasLocation W42882835341 @default.
- W4288283534 hasLocation W42882835342 @default.
- W4288283534 hasLocation W42882835343 @default.
- W4288283534 hasOpenAccess W4288283534 @default.
- W4288283534 hasPrimaryLocation W42882835341 @default.
- W4288283534 hasRelatedWork W2584377191 @default.
- W4288283534 hasRelatedWork W2891191051 @default.
- W4288283534 hasRelatedWork W2949169393 @default.
- W4288283534 hasRelatedWork W3022038857 @default.
- W4288283534 hasRelatedWork W3038067716 @default.
- W4288283534 hasRelatedWork W3170823761 @default.
- W4288283534 hasRelatedWork W4287124880 @default.
- W4288283534 hasRelatedWork W4288332995 @default.
- W4288283534 hasRelatedWork W4297740831 @default.
- W4288283534 hasRelatedWork W4319083788 @default.
- W4288283534 isParatext "false" @default.
- W4288283534 isRetracted "false" @default.
- W4288283534 workType "article" @default.