My work combines reinforcement learning, machine learning, process systems engineering, control, and applied software. Explore the systems, methods, and results behind each project.
Developed an RL-centered workflow that initializes Twin Delayed Deep Deterministic Policy Gradient (TD3) from model predictive control demonstrations, then gives the neural policy direct control and online adaptation across polymer-reactor and Aspen Dynamics C2-splitter simulations.
Designed a four-channel RL-assisted MPC architecture in which DQN and TD3 agents propose bounded controller adjustments and channel-specific critic gates decide whether to use each learned proposal or a conservative supervisor action.
Developed an RL-first control architecture in which TD3 proposes continuous coolant and monomer flow commands and a Lyapunov-guided GART-LMPC layer evaluates each move before it is applied to a simulated polymerization reactor.
A simulation-pretrained TD3 policy generated bounded acid/base flow decisions during a 4.55-hour BioSMB laboratory run across a changing pH sequence.
A measurement-hybrid 201-state hydraulic estimator uses 15 runtime fields to supply interpretable Fair and downcomer coordinates to constrained model predictive control in an Aspen Dynamics simulation.
Finance Assistance is a local-first platform that converts heterogeneous financial records into traceable accounting and read-only analytics, with guarded machine-learning categorization and a planned path toward human-reviewed AI portfolio decision support.