Matches in SemOpenAlex for { <https://semopenalex.org/work/W4288294128> ?p ?o ?g. }
Showing items 1 to 79 of
79
with 100 items per page.
- W4288294128 abstract "Deep reinforcement learning (RL) algorithms can use high-capacity deep networks to learn directly from image observations. However, these high-dimensional observation spaces present a number of challenges in practice, since the policy must now solve two problems: representation learning and task learning. In this work, we tackle these two problems separately, by explicitly learning latent representations that can accelerate reinforcement learning from images. We propose the stochastic latent actor-critic (SLAC) algorithm: a sample-efficient and high-performing RL algorithm for learning policies for complex continuous control tasks directly from high-dimensional image inputs. SLAC provides a novel and principled approach for unifying stochastic sequential models and RL into a single method, by learning a compact latent representation and then performing RL in the model's learned latent space. Our experimental evaluation demonstrates that our method outperforms both model-free and model-based alternatives in terms of final performance and sample efficiency, on a range of difficult image-based control tasks. Our code and videos of our results are available at our website." @default.
- W4288294128 created "2022-07-28" @default.
- W4288294128 creator A5026322200 @default.
- W4288294128 creator A5027666200 @default.
- W4288294128 creator A5030973600 @default.
- W4288294128 creator A5049349154 @default.
- W4288294128 date "2019-07-01" @default.
- W4288294128 modified "2023-09-25" @default.
- W4288294128 title "Stochastic Latent Actor-Critic: Deep Reinforcement Learning with a Latent Variable Model" @default.
- W4288294128 doi "https://doi.org/10.48550/arxiv.1907.00953" @default.
- W4288294128 hasPublicationYear "2019" @default.
- W4288294128 type Work @default.
- W4288294128 citedByCount "0" @default.
- W4288294128 crossrefType "posted-content" @default.
- W4288294128 hasAuthorship W4288294128A5026322200 @default.
- W4288294128 hasAuthorship W4288294128A5027666200 @default.
- W4288294128 hasAuthorship W4288294128A5030973600 @default.
- W4288294128 hasAuthorship W4288294128A5049349154 @default.
- W4288294128 hasBestOaLocation W42882941281 @default.
- W4288294128 hasConcept C108583219 @default.
- W4288294128 hasConcept C119857082 @default.
- W4288294128 hasConcept C154945302 @default.
- W4288294128 hasConcept C159985019 @default.
- W4288294128 hasConcept C162324750 @default.
- W4288294128 hasConcept C177264268 @default.
- W4288294128 hasConcept C17744445 @default.
- W4288294128 hasConcept C185592680 @default.
- W4288294128 hasConcept C187736073 @default.
- W4288294128 hasConcept C192562407 @default.
- W4288294128 hasConcept C198531522 @default.
- W4288294128 hasConcept C199360897 @default.
- W4288294128 hasConcept C199539241 @default.
- W4288294128 hasConcept C204323151 @default.
- W4288294128 hasConcept C2776359362 @default.
- W4288294128 hasConcept C2776760102 @default.
- W4288294128 hasConcept C2780451532 @default.
- W4288294128 hasConcept C41008148 @default.
- W4288294128 hasConcept C43617362 @default.
- W4288294128 hasConcept C51167844 @default.
- W4288294128 hasConcept C94625758 @default.
- W4288294128 hasConcept C97541855 @default.
- W4288294128 hasConceptScore W4288294128C108583219 @default.
- W4288294128 hasConceptScore W4288294128C119857082 @default.
- W4288294128 hasConceptScore W4288294128C154945302 @default.
- W4288294128 hasConceptScore W4288294128C159985019 @default.
- W4288294128 hasConceptScore W4288294128C162324750 @default.
- W4288294128 hasConceptScore W4288294128C177264268 @default.
- W4288294128 hasConceptScore W4288294128C17744445 @default.
- W4288294128 hasConceptScore W4288294128C185592680 @default.
- W4288294128 hasConceptScore W4288294128C187736073 @default.
- W4288294128 hasConceptScore W4288294128C192562407 @default.
- W4288294128 hasConceptScore W4288294128C198531522 @default.
- W4288294128 hasConceptScore W4288294128C199360897 @default.
- W4288294128 hasConceptScore W4288294128C199539241 @default.
- W4288294128 hasConceptScore W4288294128C204323151 @default.
- W4288294128 hasConceptScore W4288294128C2776359362 @default.
- W4288294128 hasConceptScore W4288294128C2776760102 @default.
- W4288294128 hasConceptScore W4288294128C2780451532 @default.
- W4288294128 hasConceptScore W4288294128C41008148 @default.
- W4288294128 hasConceptScore W4288294128C43617362 @default.
- W4288294128 hasConceptScore W4288294128C51167844 @default.
- W4288294128 hasConceptScore W4288294128C94625758 @default.
- W4288294128 hasConceptScore W4288294128C97541855 @default.
- W4288294128 hasLocation W42882941281 @default.
- W4288294128 hasOpenAccess W4288294128 @default.
- W4288294128 hasPrimaryLocation W42882941281 @default.
- W4288294128 hasRelatedWork W3014300295 @default.
- W4288294128 hasRelatedWork W3164822677 @default.
- W4288294128 hasRelatedWork W4223943233 @default.
- W4288294128 hasRelatedWork W4225161397 @default.
- W4288294128 hasRelatedWork W4250304930 @default.
- W4288294128 hasRelatedWork W4309045103 @default.
- W4288294128 hasRelatedWork W4312200629 @default.
- W4288294128 hasRelatedWork W4360585206 @default.
- W4288294128 hasRelatedWork W4364306694 @default.
- W4288294128 hasRelatedWork W4380086463 @default.
- W4288294128 isParatext "false" @default.
- W4288294128 isRetracted "false" @default.
- W4288294128 workType "article" @default.