vsOED uses a variational one-point reward and RL policy optimization to provide a lower bound on expected information gain for sequential experimental design, supporting nuisance parameters, implicit likelihoods, and multiple design goals.
Bayesian sequential optimal experimental design for nonlinear models using policy gradient reinforcement learning
3 Pith papers cite this work. Polarity classification is still indexing.
3
Pith papers citing it
citation-role summary
background 1
citation-polarity summary
verdicts
UNVERDICTED 3roles
background 1polarities
background 1representative citing papers
Joint dynamic programming co-optimizes continuous hardware geometry and Bellman-optimal adaptive policies, yielding large gains over baselines in radar POMDPs, qubit sensors, and 90k-pixel photonic metasensors.
A systematic survey of optimal experimental design covering criteria formulations, estimation and optimization methods, and emerging sequential design policies.
citing papers explorer
-
Variational Sequential Optimal Experimental Design using Reinforcement Learning
vsOED uses a variational one-point reward and RL policy optimization to provide a lower bound on expected information gain for sequential experimental design, supporting nuisance parameters, implicit likelihoods, and multiple design goals.
-
Adaptive Sensing beyond Non-Adaptive Information Limits: End-to-End Co-Design of Geometry, Policy, and Inference
Joint dynamic programming co-optimizes continuous hardware geometry and Bellman-optimal adaptive policies, yielding large gains over baselines in radar POMDPs, qubit sensors, and 90k-pixel photonic metasensors.
-
Optimal experimental design: Formulations and computations
A systematic survey of optimal experimental design covering criteria formulations, estimation and optimization methods, and emerging sequential design policies.