Theoretical Guarantees for Learning Conditional Expectation using Controlled ODE-RNN.

Calypso Herrera Florian Krach Josef Teichmann

Published in: CoRR (2020)

Keyphrases

theoretical guarantees
learning process
active learning
learning algorithm
multi agent systems
recurrent neural networks
reinforcement learning
objective function
dynamic programming
nearest neighbor
supervised learning
function approximation
conditional expectation