Recent Posts

Posted in Hybrid Methods

Soft Actor-Critic (SAC) Overview

Test of the layout of the page

Continue Reading...
Posted in Hybrid Methods

Twin-Delayed Deteministic Policy Gradient (TD3) Overview

Goal of TD3: Solving the overestimation bias in actor-critic methods in continuous control domain due to the function approximation error. What’s overestimation bias? Overestimation bias…

Continue Reading...
Posted in Uncategorized

DDPG Algorithm Overview

An alogirthm that deals with continous aciton space problems, combining deep learning technique with Q-learning method and deterministic policy gradient. An alogirthm that deals with…

Continue Reading...
Posted in Uncategorized

MTCS Algorithm Overview

Just a test of the website layout

Continue Reading...
Posted in Uncategorized

LaTex Formula

$latex i\hbar\frac{\partial}{\partial t}\left|\Psi(t)\right>=H\left|\Psi(t)\right>$

Continue Reading...
Posted in Uncategorized

Actor-Critic Algorithm Details

Actor-Critic integrates the value-based methods with policy-based methods to improve the learning performance.

Continue Reading...
Posted in Model-free

DQN Details

This is the most recent techque for integrating deep learning and Q-learning techniques.

Continue Reading...
Posted in Uncategorized

Hello world!

Welcome to WordPress. This is your first post. Edit or delete it, then start writing!

Continue Reading...