Matches in SemOpenAlex for { <https://semopenalex.org/work/W4306176158> ?p ?o ?g. }
Showing items 1 to 75 of
75
with 100 items per page.
- W4306176158 abstract "In-hand manipulation is challenging for a multi-finger robotic hand due to its high degrees of freedom and the complex interaction with the object. To enable in-hand manipulation, existing deep reinforcement learning based approaches mainly focus on training a single robot-structure-specific policy through the centralized learning mechanism, lacking adaptability to changes like robot malfunction. To solve this limitation, this work treats each finger as an individual agent and trains multiple agents to control their assigned fingers to complete the in-hand manipulation task cooperatively. We propose the Multi-Agent Global-Observation Critic and Local-Observation Actor (MAGCLA) method, where the critic can observe all agents' actions globally, and the actor only locally observes its neighbors' actions. Besides, conventional individual experience replay may cause unstable cooperation due to the asynchronous performance increment of each agent, which is critical for in-hand manipulation tasks. To solve this issue, we propose the Synchronized Hindsight Experience Replay (SHER) method to synchronize and efficiently reuse the replayed experience across all agents. The methods are evaluated in two in-hand manipulation tasks on the Shadow dexterous hand. The results show that SHER helps MAGCLA achieve comparable learning efficiency to a single policy, and the MAGCLA approach is more generalizable in different tasks. The trained policies have higher adaptability in the robot malfunction test compared to the baseline multi-agent and single-agent approaches." @default.
- W4306176158 created "2022-10-14" @default.
- W4306176158 creator A5012912557 @default.
- W4306176158 creator A5014940997 @default.
- W4306176158 creator A5054228072 @default.
- W4306176158 creator A5079248597 @default.
- W4306176158 date "2022-10-11" @default.
- W4306176158 modified "2023-09-27" @default.
- W4306176158 title "A Multi-Agent Approach for Adaptive Finger Cooperation in Learning-based In-Hand Manipulation" @default.
- W4306176158 doi "https://doi.org/10.48550/arxiv.2210.05767" @default.
- W4306176158 hasPublicationYear "2022" @default.
- W4306176158 type Work @default.
- W4306176158 citedByCount "0" @default.
- W4306176158 crossrefType "posted-content" @default.
- W4306176158 hasAuthorship W4306176158A5012912557 @default.
- W4306176158 hasAuthorship W4306176158A5014940997 @default.
- W4306176158 hasAuthorship W4306176158A5054228072 @default.
- W4306176158 hasAuthorship W4306176158A5079248597 @default.
- W4306176158 hasBestOaLocation W43061761581 @default.
- W4306176158 hasConcept C10347200 @default.
- W4306176158 hasConcept C107457646 @default.
- W4306176158 hasConcept C120665830 @default.
- W4306176158 hasConcept C121332964 @default.
- W4306176158 hasConcept C127413603 @default.
- W4306176158 hasConcept C151319957 @default.
- W4306176158 hasConcept C154945302 @default.
- W4306176158 hasConcept C15744967 @default.
- W4306176158 hasConcept C177606310 @default.
- W4306176158 hasConcept C180747234 @default.
- W4306176158 hasConcept C18903297 @default.
- W4306176158 hasConcept C192209626 @default.
- W4306176158 hasConcept C201995342 @default.
- W4306176158 hasConcept C2780451532 @default.
- W4306176158 hasConcept C2781238097 @default.
- W4306176158 hasConcept C31258907 @default.
- W4306176158 hasConcept C41008148 @default.
- W4306176158 hasConcept C86803240 @default.
- W4306176158 hasConcept C90509273 @default.
- W4306176158 hasConcept C97541855 @default.
- W4306176158 hasConceptScore W4306176158C10347200 @default.
- W4306176158 hasConceptScore W4306176158C107457646 @default.
- W4306176158 hasConceptScore W4306176158C120665830 @default.
- W4306176158 hasConceptScore W4306176158C121332964 @default.
- W4306176158 hasConceptScore W4306176158C127413603 @default.
- W4306176158 hasConceptScore W4306176158C151319957 @default.
- W4306176158 hasConceptScore W4306176158C154945302 @default.
- W4306176158 hasConceptScore W4306176158C15744967 @default.
- W4306176158 hasConceptScore W4306176158C177606310 @default.
- W4306176158 hasConceptScore W4306176158C180747234 @default.
- W4306176158 hasConceptScore W4306176158C18903297 @default.
- W4306176158 hasConceptScore W4306176158C192209626 @default.
- W4306176158 hasConceptScore W4306176158C201995342 @default.
- W4306176158 hasConceptScore W4306176158C2780451532 @default.
- W4306176158 hasConceptScore W4306176158C2781238097 @default.
- W4306176158 hasConceptScore W4306176158C31258907 @default.
- W4306176158 hasConceptScore W4306176158C41008148 @default.
- W4306176158 hasConceptScore W4306176158C86803240 @default.
- W4306176158 hasConceptScore W4306176158C90509273 @default.
- W4306176158 hasConceptScore W4306176158C97541855 @default.
- W4306176158 hasLocation W43061761581 @default.
- W4306176158 hasOpenAccess W4306176158 @default.
- W4306176158 hasPrimaryLocation W43061761581 @default.
- W4306176158 hasRelatedWork W1636820063 @default.
- W4306176158 hasRelatedWork W1971337054 @default.
- W4306176158 hasRelatedWork W2132787716 @default.
- W4306176158 hasRelatedWork W3007240200 @default.
- W4306176158 hasRelatedWork W3081510516 @default.
- W4306176158 hasRelatedWork W3168256553 @default.
- W4306176158 hasRelatedWork W3186584605 @default.
- W4306176158 hasRelatedWork W4229726131 @default.
- W4306176158 hasRelatedWork W4287124629 @default.
- W4306176158 hasRelatedWork W4289597918 @default.
- W4306176158 isParatext "false" @default.
- W4306176158 isRetracted "false" @default.
- W4306176158 workType "article" @default.