small updates

README.md

@@ -1,54 +1 @@
-# Researcher
 
-### [Demo Website](http://ankitsultana.com/researcher)
-
-A clean, single column, monospace resume template built for jekyll
-
-### Installation
-
-Simply fork the repository and edit away.
-
-### Customization
-
-* You can edit the `.md` (markdown) files as you see fit. You can also add some other markdown file, say `foo.md` in the root directory of the repository. It will then be accessible like so `{{ url of your website }}/foo`.
-
-* You can of course remove `contact.md` if you don't want it
-
-* To set the heading, edit the `title` variable in `_config.yml`
-
-* To edit the `links` mentioned on the navigation bar, you can edit `_config.yml`. For example:
-
-```
-nav:
- - name: "About"
-   link: "/researcher/"
- - name: "Resume"
-   link: "resume.pdf"
- - name: "Contact"
-   link: "contact"
-```
-
-* You can change the accent (color of hyperlinks) by editing the `accent` variable in `_sass/vars.scss`
-
-* You can setup google analytics, by setting `tracking_id` in `_config.yml`
-
-* To add a profile picture, make sure to give the image tag the class `profile-picture`. In other words,do it like so:
-
-```html
-<img class="profile-picture" src="sherlock.jpg">
-```
-
-* You can remove/customize the footer as you like by setting the
-appropriate variables in `_config.yml`
-
-**Note:** Customizing the accent color might cause merge conflicts if you later try to merge from `bk2dcradle/researcher` to fetch updates/patches etc. (applicable only if you have forked).
-
-#### Installation (via remote themes)
-
-* Just setting `remote_theme: ankitsultana/researcher@gem` in `_config.yml` should work. Although in that case, I am not sure how
-you would build your site locally for testing. If you know how, open up an issue and let me know.
-* For more info, [refer this](https://blog.github.com/2017-11-29-use-any-theme-with-github-pages/).
-
-### License
-
-[GNU GPL v3](https://github.com/bk2dcradle/researcher/blob/gh-pages/LICENSE)

_config.yml

@@ -1,6 +1,6 @@
 title: Adrian Millea
 url: "https://m3t4n01a.github.io"
-baseurl: "/home/"
+baseurl: "/"
 
 markdown: kramdown
 

index.md

@@ -7,19 +7,21 @@ layout: default
 <img class="profile-picture" src="me_scaled.jpg">
 
 Hi there. 
-I am a Machine Learning guy, finishing my PhD at Imperial College London under the supervision of [Abbas Edalat](https://www.doc.ic.ac.uk/~ae/). My current research topic can be very briefly summarized as "A cognitive architecture using deep learning".
+I am a Machine Learning guy, finishing my PhD at Imperial College London under the supervision of [Abbas Edalat](https://www.doc.ic.ac.uk/~ae/). My current research topic can be very briefly summarized as "Hierarchical model-based deep reinforcement learning for trading".
 
 ## Research Interests
-My main research interests *now* are in the domain of Deep Reinforcement Learning. I am interested in simple methods for non-parametric model-based reinforcement learning, semantic memory building from episodic memory using statistical properties of the environment, arbitrary hierarchical structuring of environments for planning, auxiliary reward functions, etc.
+My other research interests *now* are in the domain of Deep Reinforcement Learning. I am interested in simple methods for non-parametric model-based reinforcement learning, semantic memory building from episodic memory using statistical properties of the environment, arbitrary hierarchical structuring of environments for planning, auxiliary reward functions, etc.
 
 You can check out my longer story in the [About](/home/about) section.
 
 ## Publications
 
 1. Wiering, M. A., Schutten, M., Millea, A., Meijster, A., & Schomaker, L. R. B. (2013). Deep support vector machines for regression problems. In Proceedings of the international workshop on advances in regularization, optimization, kernel methods, and support vector machines: theory and applications. 
 2. Millea, A. (2014). Explorations in echo state networks. Department of Artificial Intelligence, Groningen University, MA, Netherlands. [pdf](Thesis_Adrian_Millea.pdf) [cite](msc.bib)
+3. Using Deep Reinforcement Learning with Hierarchical Risk Parity for Portfolio Optimization https://www.mdpi.com/2227-7072/11/1/10/pdf
+4. Deep reinforcement learning for trading—A critical survey https://www.mdpi.com/1361204
 
-## Work in progress or unpublished 
+## Unpublished work
 1. A.Millea, D.Podareanu, M.A.Wiering: Optimal action selection for the
 Foreign Exchange market using a Sarsa-Echo State Network [pdf](rl_esn.pdf) [cite](sarsa_esn.bib)
 2. A.Millea, A.Edalat: Natural Boltzmann Machines [pdf](Natural Boltzmann Machines.pdf) [cite](nbm.bib)