FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W2987388938> ?p ?o ?g. }

• W2987388938 abstract "Model-free reinforcement learning algorithms such as Deep Deterministic Policy Gradient (DDPG) often require additional exploration strategies, especially if the actor is of deterministic nature. This work evaluates the use of model-based trajectory optimization methods used for exploration in Deep Deterministic Policy Gradient when trained on a latent image embedding. In addition, an extension of DDPG is derived using a value function as critic, making use of a learned deep dynamics model to compute the policy gradient. This approach leads to a symbiotic relationship between the deep reinforcement learning algorithm and the latent trajectory optimizer. The trajectory optimizer benefits from the critic learned by the RL algorithm and the latter from the enhanced exploration generated by the planner. The developed methods are evaluated on two continuous control tasks, one in simulation and one in the real world. In particular, a Baxter robot is trained to perform an insertion task, while only receiving sparse rewards and images as observations from the environment." @default.
• W2987388938 created "2019-11-22" @default.
• W2987388938 creator A5024068845 @default.
• W2987388938 creator A5032877928 @default.
• W2987388938 creator A5040226194 @default.
• W2987388938 creator A5048668442 @default.
• W2987388938 creator A5077984643 @default.
• W2987388938 date "2019-11-15" @default.
• W2987388938 modified "2023-09-23" @default.
• W2987388938 title "Improved Exploration through Latent Trajectory Optimization in Deep Deterministic Policy Gradient" @default.
• W2987388938 cites W2016773334 @default.
• W2987388938 cites W2017957151 @default.
• W2987388938 cites W2167117957 @default.
• W2987388938 cites W2173248099 @default.
• W2987388938 cites W2561776174 @default.
• W2987388938 cites W2614839826 @default.
• W2987388938 cites W2622196250 @default.
• W2987388938 cites W2736601468 @default.
• W2987388938 cites W2741122588 @default.
• W2987388938 cites W2775490434 @default.
• W2987388938 cites W2781585732 @default.
• W2987388938 cites W2781726626 @default.
• W2987388938 cites W2795756076 @default.
• W2987388938 cites W2805762288 @default.
• W2987388938 cites W2810677299 @default.
• W2987388938 cites W2891423421 @default.
• W2987388938 cites W2894383471 @default.
• W2987388938 cites W2913938871 @default.
• W2987388938 cites W2962872206 @default.
• W2987388938 cites W2968116426 @default.
• W2987388938 cites W779494576 @default.
• W2987388938 hasPublicationYear "2019" @default.
• W2987388938 type Work @default.
• W2987388938 sameAs 2987388938 @default.
• W2987388938 citedByCount "1" @default.
• W2987388938 countsByYear W29873889382020 @default.
• W2987388938 crossrefType "posted-content" @default.
• W2987388938 hasAuthorship W2987388938A5024068845 @default.
• W2987388938 hasAuthorship W2987388938A5032877928 @default.
• W2987388938 hasAuthorship W2987388938A5040226194 @default.
• W2987388938 hasAuthorship W2987388938A5048668442 @default.
• W2987388938 hasAuthorship W2987388938A5077984643 @default.
• W2987388938 hasConcept C108583219 @default.
• W2987388938 hasConcept C121332964 @default.
• W2987388938 hasConcept C126255220 @default.
• W2987388938 hasConcept C127413603 @default.
• W2987388938 hasConcept C1276947 @default.
• W2987388938 hasConcept C13662910 @default.
• W2987388938 hasConcept C14036430 @default.
• W2987388938 hasConcept C14646407 @default.
• W2987388938 hasConcept C154945302 @default.
• W2987388938 hasConcept C178635117 @default.
• W2987388938 hasConcept C201995342 @default.
• W2987388938 hasConcept C2776999362 @default.
• W2987388938 hasConcept C2780451532 @default.
• W2987388938 hasConcept C33923547 @default.
• W2987388938 hasConcept C38652104 @default.
• W2987388938 hasConcept C41008148 @default.
• W2987388938 hasConcept C41608201 @default.
• W2987388938 hasConcept C78458016 @default.
• W2987388938 hasConcept C86803240 @default.
• W2987388938 hasConcept C89109886 @default.
• W2987388938 hasConcept C97541855 @default.
• W2987388938 hasConceptScore W2987388938C108583219 @default.
• W2987388938 hasConceptScore W2987388938C121332964 @default.
• W2987388938 hasConceptScore W2987388938C126255220 @default.
• W2987388938 hasConceptScore W2987388938C127413603 @default.
• W2987388938 hasConceptScore W2987388938C1276947 @default.
• W2987388938 hasConceptScore W2987388938C13662910 @default.
• W2987388938 hasConceptScore W2987388938C14036430 @default.
• W2987388938 hasConceptScore W2987388938C14646407 @default.
• W2987388938 hasConceptScore W2987388938C154945302 @default.
• W2987388938 hasConceptScore W2987388938C178635117 @default.
• W2987388938 hasConceptScore W2987388938C201995342 @default.
• W2987388938 hasConceptScore W2987388938C2776999362 @default.
• W2987388938 hasConceptScore W2987388938C2780451532 @default.
• W2987388938 hasConceptScore W2987388938C33923547 @default.
• W2987388938 hasConceptScore W2987388938C38652104 @default.
• W2987388938 hasConceptScore W2987388938C41008148 @default.
• W2987388938 hasConceptScore W2987388938C41608201 @default.
• W2987388938 hasConceptScore W2987388938C78458016 @default.
• W2987388938 hasConceptScore W2987388938C86803240 @default.
• W2987388938 hasConceptScore W2987388938C89109886 @default.
• W2987388938 hasConceptScore W2987388938C97541855 @default.
• W2987388938 hasOpenAccess W2987388938 @default.
• W2987388938 hasRelatedWork W1824285808 @default.
• W2987388938 hasRelatedWork W2099270968 @default.
• W2987388938 hasRelatedWork W2145957964 @default.
• W2987388938 hasRelatedWork W2548277951 @default.
• W2987388938 hasRelatedWork W2752954743 @default.
• W2987388938 hasRelatedWork W2806098286 @default.
• W2987388938 hasRelatedWork W2894422428 @default.
• W2987388938 hasRelatedWork W2924656332 @default.
• W2987388938 hasRelatedWork W2945529113 @default.
• W2987388938 hasRelatedWork W2963179943 @default.
• W2987388938 hasRelatedWork W2963864421 @default.
• W2987388938 hasRelatedWork W2969218738 @default.
• W2987388938 hasRelatedWork W3002765113 @default.
• W2987388938 hasRelatedWork W3003910700 @default.
• W2987388938 hasRelatedWork W3093511015 @default.

• next