layout: post
title: "RL"
categories: RL
tags: MBRL
comments: true

[PAPER-Review] Model-based Reinforcement learning

Table of Contents

{:.no_toc}

  1. this unordered seed list will be replaced by toc as unordered list
    {:toc}

[End-to-End Training of Deep Visuomotor Policies, Sergey, Finn, 2016]

Abstract

Keywords: RL, Optimal Control, Vision, NN

An image with a caption

[Deep Spatial Autoencoders for Visuomotor Learning, Finn, 2016]

An image with a caption

Abstract

umlcosθ+θ¨ml2mglsinθ,x¨u(7)\begin{aligned} uml cos \theta + \ddot{\theta} m l^2 - mgl sin \theta, \ddot{x} u \quad (7) \end{aligned}