Changes

Jump to: navigation, search

Allen's REINFORCE notes

325 bytes added, 24 May
Motivation
[[Category:Reinforcement Learning]]
=== Motivation ===  Recall that the objective of Reinforcement Learning is to find an optimal policy <math>\pi^*<\math> which we encode in a neural network with parameters <math>\theta^*<\math>. These optimal parameters are defined as<math>\theta^* = \text<argmax>_\theta E_{\tau \sim p_\theta(\tau)} \left[ \sum_t r(s_t, a_t) \right] <\math> 
=== Learning ===
53
edits

Navigation menu