Matches in SemOpenAlex for { <https://semopenalex.org/work/W4320342078> ?p ?o ?g. }
Showing items 1 to 53 of
53
with 100 items per page.
- W4320342078 abstract "This paper introduces the Hamilton-Jacobi-Bellman Proximal Policy Optimization (HJBPPO) algorithm into reinforcement learning. The Hamilton-Jacobi-Bellman (HJB) equation is used in control theory to evaluate the optimality of the value function. Our work combines the HJB equation with reinforcement learning in continuous state and action spaces to improve the training of the value network. We treat the value network as a Physics-Informed Neural Network (PINN) to solve for the HJB equation by computing its derivatives with respect to its inputs exactly. The Proximal Policy Optimization (PPO)-Clipped algorithm is improvised with this implementation as it uses a value network to compute the objective function for its policy network. The HJBPPO algorithm shows an improved performance compared to PPO on the MuJoCo environments." @default.
- W4320342078 created "2023-02-13" @default.
- W4320342078 creator A5027835055 @default.
- W4320342078 creator A5082477628 @default.
- W4320342078 date "2023-01-31" @default.
- W4320342078 modified "2023-09-23" @default.
- W4320342078 title "Bridging Physics-Informed Neural Networks with Reinforcement Learning: Hamilton-Jacobi-Bellman Proximal Policy Optimization (HJBPPO)" @default.
- W4320342078 doi "https://doi.org/10.48550/arxiv.2302.00237" @default.
- W4320342078 hasPublicationYear "2023" @default.
- W4320342078 type Work @default.
- W4320342078 citedByCount "0" @default.
- W4320342078 crossrefType "posted-content" @default.
- W4320342078 hasAuthorship W4320342078A5027835055 @default.
- W4320342078 hasAuthorship W4320342078A5082477628 @default.
- W4320342078 hasBestOaLocation W43203420781 @default.
- W4320342078 hasConcept C126255220 @default.
- W4320342078 hasConcept C14646407 @default.
- W4320342078 hasConcept C154945302 @default.
- W4320342078 hasConcept C174348530 @default.
- W4320342078 hasConcept C196978813 @default.
- W4320342078 hasConcept C31258907 @default.
- W4320342078 hasConcept C33923547 @default.
- W4320342078 hasConcept C41008148 @default.
- W4320342078 hasConcept C50644808 @default.
- W4320342078 hasConcept C91575142 @default.
- W4320342078 hasConcept C97541855 @default.
- W4320342078 hasConceptScore W4320342078C126255220 @default.
- W4320342078 hasConceptScore W4320342078C14646407 @default.
- W4320342078 hasConceptScore W4320342078C154945302 @default.
- W4320342078 hasConceptScore W4320342078C174348530 @default.
- W4320342078 hasConceptScore W4320342078C196978813 @default.
- W4320342078 hasConceptScore W4320342078C31258907 @default.
- W4320342078 hasConceptScore W4320342078C33923547 @default.
- W4320342078 hasConceptScore W4320342078C41008148 @default.
- W4320342078 hasConceptScore W4320342078C50644808 @default.
- W4320342078 hasConceptScore W4320342078C91575142 @default.
- W4320342078 hasConceptScore W4320342078C97541855 @default.
- W4320342078 hasLocation W43203420781 @default.
- W4320342078 hasOpenAccess W4320342078 @default.
- W4320342078 hasPrimaryLocation W43203420781 @default.
- W4320342078 hasRelatedWork W1863485266 @default.
- W4320342078 hasRelatedWork W2149174258 @default.
- W4320342078 hasRelatedWork W2172170808 @default.
- W4320342078 hasRelatedWork W2766998270 @default.
- W4320342078 hasRelatedWork W2787184676 @default.
- W4320342078 hasRelatedWork W2803623613 @default.
- W4320342078 hasRelatedWork W2889834506 @default.
- W4320342078 hasRelatedWork W2981246288 @default.
- W4320342078 hasRelatedWork W3046256638 @default.
- W4320342078 hasRelatedWork W4289419495 @default.
- W4320342078 isParatext "false" @default.
- W4320342078 isRetracted "false" @default.
- W4320342078 workType "article" @default.