Graduate Descent

About
Archive

Tag: rl

2019

The likelihood-ratio gradient

Apr 20 2019

optimization rl machine-learning

Recent Posts

The likelihood-ratio gradient

Tags

numerical, efficiency, sampling-without-replacement, statistics, notebook, ordered-sampling, sampling, algorithms, Gumbel, decision-making, reservoir-sampling, optimization, rl, machine-learning, calculus, automatic-differentiation, implicit-function-theorem, Lagrange-multipliers, testing, counterfactual-reasoning, importance-sampling, datastructures, incremental-computation, data-structures, rant, hyperparameter-optimization, crf, deep-learning, structured-prediction, visualization

Copyright © 2019 Tim Vieira — Powered by Pelican