Search Results for author:
Found 5 papers, 0 papers with code
Towards Hyperparameter-Agnostic DNN Training via Dynamical System Insights
We present a stochastic first-order optimization method specialized for deep neural networks (DNNs), ECCO-DNN.
Model-Free Learning and Optimal Policy Design in Multi-Agent MDPs Under Probabilistic Agent Dropout
The controller's objective is to find an optimal policy that maximizes the value of the expected system given a priori knowledge of the agents' dropout probabilities.
Corrected: On Confident Policy Evaluation for Factored Markov Decision Processes with Node Dropouts
In this work we investigate an importance sampling approach for evaluating policies for a structurally time-varying factored Markov decision process (MDP), i. e. the policy's value is estimated with a high-probability confidence interval.
ECCO: Equivalent Circuit Controlled Optimization
To find the value of the critical point, we propose a time step search routine for Forward Euler discretization that controls the local truncation error, a method adapted from circuit simulation ideas.
Cluster-Based Control of Transition-Independent MDPs
To efficiently find a policy in this rapidly scaling space, we propose a clustered Bellman operator that optimizes over the action space for one cluster at any evaluation.
