Matches in SemOpenAlex for { <https://semopenalex.org/work/W3210713039> ?p ?o ?g. }
Showing items 1 to 80 of
80
with 100 items per page.
- W3210713039 abstract "Developing behavior based robotic manipulation is a very challenging but necessary task to be solved, especially for humanoid and social robots. Fundamental robotic tasks such as grasping, pick and place, trajectory following are at present solved using conventional forward and inverse kinematics (IK), dynamics and trajectory planning, whereas we learn these complex tasks using past experiences. In this paper, we explore developing behavior based robotic manipulation using reinforcement learning, more specifically learning directly from experiences through interactions with the real world and without knowing the transition model of the environment. Here, we propose a multi agent paradigm to gather experiences from multiple environments in parallel along with a model for populating new generation of agents using Evolutionary Actor-Critic Algorithm (EACA). The agents are of actor-critic architecture and both of them comprises of general purpose neural networks. The actor-critic architecture enables the model to perform well both in high dimensional state space and high dimensional action space which is very crucial for all robotic applications. The proposed algorithm is benchmarked with respect to different multi agent paradigm but keeping the agent’s architecture same. Reinforcement learning, being highly data intensive, requires the use of the CPU and GPU cores to be done judiciously for sampling the environment as well as for training, the details of which have been described here. We have run rigorous experiments for learning joint trajectories on the open gym based KUKA arm manipulator, where our proposed method achieves learning stability within 300 episodes, as compared to the state-of-the-art actor-critic and Advanced Asynchronous Actor-Critic (A3C) algorithms both of which take more than 1000 episodes for learning the same task, showing the effectiveness of our proposed model." @default.
- W3210713039 created "2021-11-08" @default.
- W3210713039 creator A5017976301 @default.
- W3210713039 creator A5059369765 @default.
- W3210713039 creator A5076307665 @default.
- W3210713039 date "2021-08-26" @default.
- W3210713039 modified "2023-10-03" @default.
- W3210713039 title "Development of Behavior based Robot manipulation using Actor-Critic architecture" @default.
- W3210713039 cites W1977655452 @default.
- W3210713039 cites W2805051407 @default.
- W3210713039 cites W2938421504 @default.
- W3210713039 cites W2947299120 @default.
- W3210713039 cites W2962759351 @default.
- W3210713039 doi "https://doi.org/10.1109/spin52536.2021.9566102" @default.
- W3210713039 hasPublicationYear "2021" @default.
- W3210713039 type Work @default.
- W3210713039 sameAs 3210713039 @default.
- W3210713039 citedByCount "1" @default.
- W3210713039 countsByYear W32107130392023 @default.
- W3210713039 crossrefType "proceedings-article" @default.
- W3210713039 hasAuthorship W3210713039A5017976301 @default.
- W3210713039 hasAuthorship W3210713039A5059369765 @default.
- W3210713039 hasAuthorship W3210713039A5076307665 @default.
- W3210713039 hasConcept C105795698 @default.
- W3210713039 hasConcept C112972136 @default.
- W3210713039 hasConcept C119857082 @default.
- W3210713039 hasConcept C121332964 @default.
- W3210713039 hasConcept C123657996 @default.
- W3210713039 hasConcept C127413603 @default.
- W3210713039 hasConcept C1276947 @default.
- W3210713039 hasConcept C13662910 @default.
- W3210713039 hasConcept C142362112 @default.
- W3210713039 hasConcept C153349607 @default.
- W3210713039 hasConcept C154945302 @default.
- W3210713039 hasConcept C17816587 @default.
- W3210713039 hasConcept C201995342 @default.
- W3210713039 hasConcept C2780451532 @default.
- W3210713039 hasConcept C33923547 @default.
- W3210713039 hasConcept C41008148 @default.
- W3210713039 hasConcept C60692881 @default.
- W3210713039 hasConcept C72434380 @default.
- W3210713039 hasConcept C90509273 @default.
- W3210713039 hasConcept C97541855 @default.
- W3210713039 hasConceptScore W3210713039C105795698 @default.
- W3210713039 hasConceptScore W3210713039C112972136 @default.
- W3210713039 hasConceptScore W3210713039C119857082 @default.
- W3210713039 hasConceptScore W3210713039C121332964 @default.
- W3210713039 hasConceptScore W3210713039C123657996 @default.
- W3210713039 hasConceptScore W3210713039C127413603 @default.
- W3210713039 hasConceptScore W3210713039C1276947 @default.
- W3210713039 hasConceptScore W3210713039C13662910 @default.
- W3210713039 hasConceptScore W3210713039C142362112 @default.
- W3210713039 hasConceptScore W3210713039C153349607 @default.
- W3210713039 hasConceptScore W3210713039C154945302 @default.
- W3210713039 hasConceptScore W3210713039C17816587 @default.
- W3210713039 hasConceptScore W3210713039C201995342 @default.
- W3210713039 hasConceptScore W3210713039C2780451532 @default.
- W3210713039 hasConceptScore W3210713039C33923547 @default.
- W3210713039 hasConceptScore W3210713039C41008148 @default.
- W3210713039 hasConceptScore W3210713039C60692881 @default.
- W3210713039 hasConceptScore W3210713039C72434380 @default.
- W3210713039 hasConceptScore W3210713039C90509273 @default.
- W3210713039 hasConceptScore W3210713039C97541855 @default.
- W3210713039 hasLocation W32107130391 @default.
- W3210713039 hasOpenAccess W3210713039 @default.
- W3210713039 hasPrimaryLocation W32107130391 @default.
- W3210713039 hasRelatedWork W1974658529 @default.
- W3210713039 hasRelatedWork W1974960581 @default.
- W3210713039 hasRelatedWork W2243991451 @default.
- W3210713039 hasRelatedWork W2626492911 @default.
- W3210713039 hasRelatedWork W2775515444 @default.
- W3210713039 hasRelatedWork W2980585282 @default.
- W3210713039 hasRelatedWork W2999902861 @default.
- W3210713039 hasRelatedWork W3010835448 @default.
- W3210713039 hasRelatedWork W3138568041 @default.
- W3210713039 hasRelatedWork W4206218156 @default.
- W3210713039 isParatext "false" @default.
- W3210713039 isRetracted "false" @default.
- W3210713039 magId "3210713039" @default.
- W3210713039 workType "article" @default.