Justin Dixon

Economist

Biography

Justin Dixon is a recent graduate from the University of Sydney. He studied his Master of Economic Analysis and focused his studies on micro economic theory and applied micro economics. For his research thesis he researched various applications of contest theory with novel data from professional Dota 2 matches.

After graduating with his Bachelors Justin spent a year travelling and working in Europe. After returning to Australia he worked briefly as a tax accountant before training to become an economist.

Interests

Applied Micro
Contest Theory
Artificial Intelligence

Education

Master of Economic Analysis, 2017

The University of Sydney
BCom in Economics and Finance, 2012

The University of Sydney

Algorithm

Example

Policy Improvement

Algorithm

Example

Policy Iteration

Algorithm

Example

Value Iteration

Algorithm

Example

Asynchronous Dynamic Programming

Dont sweep the entire state space.

Generalized Policy Iteration

evaluation then improvement then evaluation then improvement then evaluation

Feb 10, 2018 2 min read Reinforcement Learning

Finite Markov Decision Processes: Chapter 3 IRL

Introduction In Markov Decision Processes you have: * Agent: The decision maker / learner. The agent sends an action to the environment. * Environment: Everything that is not the agent. The environment sends a reward back to the agent. * Reward: The signal that agent tries to maximize. Example GridWorld Lets say we have a 5x5 grid. There are four possible actions: left, right, up, and down. If you reach the point (1,2) and move in any direction you recieve the reward of 10 and are moved to the point (5,2).

Feb 10, 2018 1 min read Reinforcement Learning

Monte Carlo Methods: Chapter 5 IRL

R Markdown This is an R Markdown document. Markdown is a simple formatting syntax for authoring HTML, PDF, and MS Word documents. For more details on using R Markdown see http://rmarkdown.rstudio.com. When you click the Knit button a document will be generated that includes both content as well as the output of any embedded R code chunks within the document. You can embed an R code chunk like this: summary(cars) Including Plots You can also embed plots, for example:

Economics / Data Analysis

Justin Dixon

Economist

Biography

Interests

Education

Recent Posts

Contest Theory

Discouragement Effect

Dynamic Programming: Chapter 4 IRL

Introduction

Policy Evaluation (Prediction)

Algorithm

Example

Policy Improvement

Algorithm

Example

Policy Iteration

Algorithm

Example

Value Iteration

Algorithm

Example

Asynchronous Dynamic Programming

Generalized Policy Iteration

Finite Markov Decision Processes: Chapter 3 IRL

Monte Carlo Methods: Chapter 5 IRL

Recent Publications

Projects

Contact

Tags