rlworkgroup/garage

Split GaussianMLPModel into several variants

开放

#587 创建于 2019年3月19日

 (0 条评论) (0 个反应) (0 位负责人)Python (297 个派生)batch import
good first issuetf

仓库指标

星标
 (1,728 个星标)
PR 合并指标
 (30 天内没有已合并 PR)

描述

The current GaussianMLPModel actually represents several architecture variants, which makes it difficult to use and to test. We should split it into several variants based on architecture (and possibly parameterization)

description mean std_param
fixed variance MLP1 parameter (trainable or not)
split network MLP1 MLP2
shared network/multi-headed MLP1/head1 MLP1/head2

贡献者指南