In this paper, motivated by human neurocognitive experiments, a model-free off-policy reinforcement learning algorithm is developed to solve the optimal tracking control of multiple-model linear discrete-time systems. First, an adaptive self-organizing map neural network is used to determine the system behavior from measured data and to assign a responsibility signal to each of system possible behaviors. A new model is added if a sudden change of system behavior is detected from the measured data and the behavior has not been previously detected. A value function is represented by partially weighted value functions. Then, the off-policy iteration algorithm is generalized to multiple-model learning to find a solution without any knowledge about the system dynamics or reference trajectory dynamics. The off-policy approach helps to increase data efficiency and speed of tuning since a stream of experiences obtained from executing a behavior policy is reused to update several value functions corresponding to different learning policies sequentially. Two numerical examples serve as a demonstration of the off-policy algorithm performance.
Download full-text PDF |
Source |
|---|---|
| http://dx.doi.org/10.1109/TCYB.2016.2618926 | DOI Listing |
Publication Analysis
Top Keywords
Similar Publications
Square Root Unscented Kalman Filter-Based Multiple-Model Fault Diagnosis of PEM Fuel Cells.
Sensors (Basel)
December 2024
Institute of Autmatic Control, University of Kaiserslautern-Landau, 67653 Kaiserslautern, Germany.
Harsh operating conditions imposed by vehicular applications significantly limit the utilization of proton exchange membrane fuel cells (PEMFCs) in electric propulsion systems. Improper/poor management and supervision of rapidly varying current demands can lead to undesired electrochemical reactions and critical cell failures. Among other failures, flooding and catalytic degradation are failure mechanisms that directly impact the composition of the membrane electrode assembly and can cause irreversible cell performance deterioration.
View Article and Find Full Text PDFAmplifying Ca overload by engineered biomaterials for synergistic cancer therapy.
Biomaterials
May 2025
Department of Radiology, Sir Run Run Shaw Hospital, Zhejiang University School of Medicine, Hangzhou, 310016, China; Key Laboratory for Biomedical Engineering of Ministry of Education, Zhejiang University, China; Cancer Center, Zhejiang University, Hangzhou, Zhejiang, 310058, China. Electronic address:
Ca overload is one of the most widely causes of inducing apoptosis, pyroptosis, immunogenic cell death, autophagy, paraptosis, necroptosis, and calcification of tumor cells, and has become the most valuable therapeutic strategy in the field of cancer treatment. Nevertheless, several challenges remain in translating Ca overload-mediated therapeutic strategies into clinical applications, such as the precise control of Ca dynamics, specificity of Ca homeostasis dysregulation, as well as comprehensive mechanisms of Ca regulation. Given this, we comprehensively reviewed the Ca-driven intracellular signaling pathways and the application of Ca-based biomaterials (such as CaCO-, CaP-, CaO-, CaSi-, CaF-, and CaH-) in mediating cancer diagnosis, treatment, and immunotherapy.
View Article and Find Full Text PDFAdaptive multi-model predictive control with optimal model bank formation: Consideration of local models uncertainty and stability.
Heliyon
November 2024
Electrical Engineering Department, Iran University of Science and Technology, Narmak, Tehran, Iran.
The Multiple Model Control (MMC) structure comprises three main components: the model bank, controller bank, and supervisor algorithm. Precise design of these components is crucial for achieving high control performance within the MMC framework, albeit this effort is not without its challenges. These challenges involve optimizing the model and controller banks ensuring system stability when dealing with uncertainties in the local models and enabling smooth switching between model-controller pairs.
View Article and Find Full Text PDFMild Traumatic Brain Injury and Criminal Charges and Convictions in Mid and Late Adolescence.
JAMA Pediatr
November 2024
ROCKWOOL Foundation, Copenhagen, Denmark.
Article Synopsis
- Childhood exposure to mild traumatic brain injury (mTBI) has been linked to increased involvement in criminal justice as adolescents and adults, but previous studies haven't established whether this connection is causal or just a coincidence.
- This study aimed to determine if childhood mTBI directly causes later criminal justice involvement, using a large population-based cohort from Denmark, tracking health and legal data from 1995 to 2000.
- Results showed that out of 343,027 participants, there was a positive association between a history of mTBI and increased criminal charges, suggesting a potential causal link warranting further investigation.
Functional connectivity subtypes during a positive mood induction: Predicting clinical response in a randomized controlled trial of ketamine for treatment-resistant depression.
J Psychopathol Clin Sci
September 2024
Department of Psychiatry, University of Pittsburgh School of Medicine.
Article Synopsis
- * This study analyzed brain connectivity during positive mood processing to classify TRD patients into two subgroups before they received either ketamine or saline infusion.
- * Results indicated that while ketamine was effective for both subgroups in improving depression, the identified subgroups significantly influenced the response to the saline placebo treatment.
Want AI Summaries of new PubMed Abstracts delivered to your In-box?
Enter search terms and have AI summaries delivered each week - change queries or unsubscribe any time!