3.14. SequentialLearning.Algorithms.RandomSampling.Tendsto
Random Sampling convergence lemmas
This file contains several convergence lemmas for the randomSampling algorithm along with an
evalEnv environment, that evaluates the actions using a measurable function.
Main statements
-
hasLaw_feeback: Each feedback follows the distribution μ.map f. -
iIndep_feedback: Feedbacks are mutually independent across time steps. -
action_tendsto_any: The minimum distance from sampled actions to any point in α tends to zero in measure. -
feedback_tendsto_any: The minimum distance from rewards to any value offtends to zero in measure. -
tendsto_min: The minimum reward converges in measure to the global minimum value. -
tendsto_max: The maximum reward converges in measure to the global maximum value.
Module LeanMachineLearning.SequentialLearning.Algorithms.RandomSampling.Tendsto contains 9 exposed declarations.
-
Learning.randomSampling.hasLaw_feeback -
Learning.randomSampling.iIndep_feedback -
Learning.randomSampling.action_tendsto_any -
Learning.randomSampling.image_action_tendsto_any -
Learning.randomSampling.feedback_tendsto_any -
Learning.randomSampling.tendsto_min₀ -
Learning.randomSampling.tendsto_min -
Learning.randomSampling.tendsto_max₀ -
Learning.randomSampling.tendsto_max