Matches in SemOpenAlex for { <https://semopenalex.org/work/W4382936027> ?p ?o ?g. }
Showing items 1 to 86 of
86
with 100 items per page.
- W4382936027 abstract "Reinforcement learning (RL) control for nonlinear dynamical systems has seen increasing interests in recent years. However, these methods have limited practical use due to the lack of safety and stability guarantees of the control policy. In this paper, we employ a control-theoretic approach to the stability of RL-based control. We propose a two-step framework to train a Deep Deterministic Policy Gradient (DDPG) agent regulated on the violations of the Lyapunov conditions. In the first step, our framework leverages neural networks to jointly learn stable system dynamics and an associated control-Lyapunov function (cLf) based on the current control policy. In the second step, a DDPG controller is trained to learn an appropriate control policy that maximizes the reward function and minimizes the violation of the Lyapunov condition based on the current iteration of the cLf. We employ a model of dynamics noise when learning the cLf to improve the exploration of alternative state trajectories. The proposed framework is tested on nonlinear vehicle dynamics in a lane-following highway environment. The experimental results demonstrate the ability of the proposed framework to regulate the control policy on learning stable system trajectories with desired driving characteristics." @default.
- W4382936027 created "2023-07-04" @default.
- W4382936027 creator A5011631732 @default.
- W4382936027 creator A5024559779 @default.
- W4382936027 date "2023-05-31" @default.
- W4382936027 modified "2023-09-25" @default.
- W4382936027 title "Lyapunov Stability Regulation of Deep Reinforcement Learning Control with Application to Automated Driving" @default.
- W4382936027 cites W2017957151 @default.
- W4382936027 cites W2049110508 @default.
- W4382936027 cites W2137983211 @default.
- W4382936027 cites W2162419813 @default.
- W4382936027 cites W2616635592 @default.
- W4382936027 cites W2909414402 @default.
- W4382936027 cites W2963322416 @default.
- W4382936027 cites W2991448601 @default.
- W4382936027 cites W2995343962 @default.
- W4382936027 cites W3034445502 @default.
- W4382936027 cites W3037593164 @default.
- W4382936027 cites W3115648115 @default.
- W4382936027 cites W3145799606 @default.
- W4382936027 doi "https://doi.org/10.23919/acc55779.2023.10155918" @default.
- W4382936027 hasPublicationYear "2023" @default.
- W4382936027 type Work @default.
- W4382936027 citedByCount "0" @default.
- W4382936027 crossrefType "proceedings-article" @default.
- W4382936027 hasAuthorship W4382936027A5011631732 @default.
- W4382936027 hasAuthorship W4382936027A5024559779 @default.
- W4382936027 hasConcept C112972136 @default.
- W4382936027 hasConcept C119857082 @default.
- W4382936027 hasConcept C121332964 @default.
- W4382936027 hasConcept C127413603 @default.
- W4382936027 hasConcept C133731056 @default.
- W4382936027 hasConcept C14036430 @default.
- W4382936027 hasConcept C154945302 @default.
- W4382936027 hasConcept C158622935 @default.
- W4382936027 hasConcept C201030206 @default.
- W4382936027 hasConcept C203479927 @default.
- W4382936027 hasConcept C2775924081 @default.
- W4382936027 hasConcept C37935115 @default.
- W4382936027 hasConcept C41008148 @default.
- W4382936027 hasConcept C47446073 @default.
- W4382936027 hasConcept C50644808 @default.
- W4382936027 hasConcept C60640748 @default.
- W4382936027 hasConcept C62520636 @default.
- W4382936027 hasConcept C6557445 @default.
- W4382936027 hasConcept C78458016 @default.
- W4382936027 hasConcept C86803240 @default.
- W4382936027 hasConcept C97541855 @default.
- W4382936027 hasConceptScore W4382936027C112972136 @default.
- W4382936027 hasConceptScore W4382936027C119857082 @default.
- W4382936027 hasConceptScore W4382936027C121332964 @default.
- W4382936027 hasConceptScore W4382936027C127413603 @default.
- W4382936027 hasConceptScore W4382936027C133731056 @default.
- W4382936027 hasConceptScore W4382936027C14036430 @default.
- W4382936027 hasConceptScore W4382936027C154945302 @default.
- W4382936027 hasConceptScore W4382936027C158622935 @default.
- W4382936027 hasConceptScore W4382936027C201030206 @default.
- W4382936027 hasConceptScore W4382936027C203479927 @default.
- W4382936027 hasConceptScore W4382936027C2775924081 @default.
- W4382936027 hasConceptScore W4382936027C37935115 @default.
- W4382936027 hasConceptScore W4382936027C41008148 @default.
- W4382936027 hasConceptScore W4382936027C47446073 @default.
- W4382936027 hasConceptScore W4382936027C50644808 @default.
- W4382936027 hasConceptScore W4382936027C60640748 @default.
- W4382936027 hasConceptScore W4382936027C62520636 @default.
- W4382936027 hasConceptScore W4382936027C6557445 @default.
- W4382936027 hasConceptScore W4382936027C78458016 @default.
- W4382936027 hasConceptScore W4382936027C86803240 @default.
- W4382936027 hasConceptScore W4382936027C97541855 @default.
- W4382936027 hasFunder F4320306108 @default.
- W4382936027 hasLocation W43829360271 @default.
- W4382936027 hasOpenAccess W4382936027 @default.
- W4382936027 hasPrimaryLocation W43829360271 @default.
- W4382936027 hasRelatedWork W1574878188 @default.
- W4382936027 hasRelatedWork W2156135399 @default.
- W4382936027 hasRelatedWork W2320719555 @default.
- W4382936027 hasRelatedWork W2356450042 @default.
- W4382936027 hasRelatedWork W2367526667 @default.
- W4382936027 hasRelatedWork W2375061895 @default.
- W4382936027 hasRelatedWork W2907195160 @default.
- W4382936027 hasRelatedWork W2986542767 @default.
- W4382936027 hasRelatedWork W4249223635 @default.
- W4382936027 hasRelatedWork W4372294702 @default.
- W4382936027 isParatext "false" @default.
- W4382936027 isRetracted "false" @default.
- W4382936027 workType "article" @default.