Matches in SemOpenAlex for { <https://semopenalex.org/work/W4313288839> ?p ?o ?g. }
Showing items 1 to 83 of
83
with 100 items per page.
- W4313288839 abstract "In recent years, the motion planning algorithm based on reinforcement learning has shown its potential to meet the requirements of high-dimensional planning space, complex task environments, and fast online planning simultaneously. However, the performance of the reinforcement learning-based motion planning algorithm for manipulators is closely related to the quality of the reward function, which is typically designed manually. In this paper, inspired by heuristic functions, a new learning-based reward function design framework is proposed. By relaxing the constraint of the original motion planning problem, a simple task is established. The cost of a solution to the simple task is taken as a heuristic for the original problem, and the heuristic is then incorporated into the reward function. We tested the performance of heuristic-guided reward functions based on the soft-actor-critic algorithm in various difficult scenarios. The experimental results showed that our reward function design method improves the convergence speed of the reinforcement learning training process and the planning success rate of the policy obtained after the training. In addition, the trained motion planning policy could be directly transferred to a real manipulator for online execution without modification, thus verifying the flexibility of the strategy between simulated and real environments." @default.
- W4313288839 created "2023-01-06" @default.
- W4313288839 creator A5054021565 @default.
- W4313288839 creator A5073181963 @default.
- W4313288839 creator A5091543149 @default.
- W4313288839 date "2022-10-28" @default.
- W4313288839 modified "2023-09-25" @default.
- W4313288839 title "Heuristic Reward Function for Reinforcement Learning Based Manipulator Motion Planning" @default.
- W4313288839 cites W1140243306 @default.
- W4313288839 cites W1559814819 @default.
- W4313288839 cites W2009812633 @default.
- W4313288839 cites W2099893201 @default.
- W4313288839 cites W2119562960 @default.
- W4313288839 cites W212119337 @default.
- W4313288839 cites W2128990851 @default.
- W4313288839 cites W2164276476 @default.
- W4313288839 cites W2419216244 @default.
- W4313288839 cites W2894417726 @default.
- W4313288839 cites W2905251894 @default.
- W4313288839 cites W2963572779 @default.
- W4313288839 cites W2967969632 @default.
- W4313288839 cites W2979290707 @default.
- W4313288839 cites W3005431655 @default.
- W4313288839 cites W3106159194 @default.
- W4313288839 cites W61873113 @default.
- W4313288839 doi "https://doi.org/10.1109/icus55513.2022.9986816" @default.
- W4313288839 hasPublicationYear "2022" @default.
- W4313288839 type Work @default.
- W4313288839 citedByCount "0" @default.
- W4313288839 crossrefType "proceedings-article" @default.
- W4313288839 hasAuthorship W4313288839A5054021565 @default.
- W4313288839 hasAuthorship W4313288839A5073181963 @default.
- W4313288839 hasAuthorship W4313288839A5091543149 @default.
- W4313288839 hasConcept C104114177 @default.
- W4313288839 hasConcept C105795698 @default.
- W4313288839 hasConcept C119857082 @default.
- W4313288839 hasConcept C127413603 @default.
- W4313288839 hasConcept C14036430 @default.
- W4313288839 hasConcept C154945302 @default.
- W4313288839 hasConcept C173801870 @default.
- W4313288839 hasConcept C201995342 @default.
- W4313288839 hasConcept C2780451532 @default.
- W4313288839 hasConcept C2780598303 @default.
- W4313288839 hasConcept C33923547 @default.
- W4313288839 hasConcept C41008148 @default.
- W4313288839 hasConcept C78458016 @default.
- W4313288839 hasConcept C81074085 @default.
- W4313288839 hasConcept C86803240 @default.
- W4313288839 hasConcept C90509273 @default.
- W4313288839 hasConcept C97541855 @default.
- W4313288839 hasConceptScore W4313288839C104114177 @default.
- W4313288839 hasConceptScore W4313288839C105795698 @default.
- W4313288839 hasConceptScore W4313288839C119857082 @default.
- W4313288839 hasConceptScore W4313288839C127413603 @default.
- W4313288839 hasConceptScore W4313288839C14036430 @default.
- W4313288839 hasConceptScore W4313288839C154945302 @default.
- W4313288839 hasConceptScore W4313288839C173801870 @default.
- W4313288839 hasConceptScore W4313288839C201995342 @default.
- W4313288839 hasConceptScore W4313288839C2780451532 @default.
- W4313288839 hasConceptScore W4313288839C2780598303 @default.
- W4313288839 hasConceptScore W4313288839C33923547 @default.
- W4313288839 hasConceptScore W4313288839C41008148 @default.
- W4313288839 hasConceptScore W4313288839C78458016 @default.
- W4313288839 hasConceptScore W4313288839C81074085 @default.
- W4313288839 hasConceptScore W4313288839C86803240 @default.
- W4313288839 hasConceptScore W4313288839C90509273 @default.
- W4313288839 hasConceptScore W4313288839C97541855 @default.
- W4313288839 hasLocation W43132888391 @default.
- W4313288839 hasOpenAccess W4313288839 @default.
- W4313288839 hasPrimaryLocation W43132888391 @default.
- W4313288839 hasRelatedWork W2134304017 @default.
- W4313288839 hasRelatedWork W2577672356 @default.
- W4313288839 hasRelatedWork W2981830920 @default.
- W4313288839 hasRelatedWork W3173665782 @default.
- W4313288839 hasRelatedWork W4213361106 @default.
- W4313288839 hasRelatedWork W4288089255 @default.
- W4313288839 hasRelatedWork W4309786668 @default.
- W4313288839 hasRelatedWork W4319083788 @default.
- W4313288839 hasRelatedWork W4366563806 @default.
- W4313288839 hasRelatedWork W2189342182 @default.
- W4313288839 isParatext "false" @default.
- W4313288839 isRetracted "false" @default.
- W4313288839 workType "article" @default.