Pedro A. Ortega
http://www.adaptiveagents.org/
2015-03-26T15:06:17-04:00Pedro A. Ortega
http://www.adaptiveagents.org/
http://www.adaptiveagents.org/ttp://www.adaptiveagents.org/lib/tpl/dokuwiki/images/favicon.icotext/html2015-03-23T09:43:05-04:00peortegaInformation-Theoretic Bounded Rationality - [References]
http://www.adaptiveagents.org/freeenergy?rev=1427118185
Slides from my last talk: [PDF].
Bounded rationality is an active field of research in economics with important implications not only to behavioral economics, but also to computational neuroscience and especially artificial intelligence. In artificial intelligence, such a theory would provide a principled basis for the construction of controllers under resource limitations, which is widely regarded as one of the most important open problems of artificial intelligence. Needless to say, there is …text/html2015-03-07T01:15:56-04:00peortegaCV and Bio - [Curriculum Vitae]
http://www.adaptiveagents.org/bio?rev=1425708956
Curriculum Vitae
Curriculum Vitae [[PDF]] (updated 7 March 2015)
Short Bio
Pedro A. Ortega is postdoctoral researcher at the GRASP Robotics Lab, University of Pennsylvania, working with Prof. Daniel D. Lee. His research focuses on the mathematical foundations of artificial intelligence, machine learning and cybernetics. His work includes the application of information-theoretic and statistical mechanical ideas to sequential decision-making, which has led to contributions in novel bounded ra…text/html2015-03-07T01:15:38-04:00peortegacv-english.pdf
http://www.adaptiveagents.org/?image=cv-english.pdf&ns=&rev=1425708938&do=media
text/html2015-03-04T22:49:42-04:00peortegaPublications - [2015]
http://www.adaptiveagents.org/publications?rev=1425527382
The :!: denotes my favourite (or most representative) works.
Theses
[2] Ortega, P.A.
:!: A Unified Framework for Resource-Bounded Autonomous Agents Interacting with Unknown Environments
PhD Thesis, Dept. of Engineering, University of Cambridge, 2011.
Thesis supervisor: Zoubin Ghahramani
Thesis committee: Marcus Hutter and Carl E. Rasmussen
[[PDF]]text/html2015-02-25T17:33:38-04:00peortegaPedro A. Ortega - [About]
http://www.adaptiveagents.org/home?rev=1424903618
Postdoc
School of Engineering and Applied Sciences
University of Pennsylvania
[This is Ludwig Boltzmann (no joke). There' s something about it. Thanks to Jordi for pointing it out!]
About
I am a postdoc at the University of Pennsylvania. I got my PhD in Engineering from the University of Cambridge and my BSc/Diploma in Computer Engineering from the University of Chile. My background is mainly in Physics, Mathematics and Computer Science.text/html2015-02-22T19:01:15-04:00peortegaMDPs Using Bayesian Control Rule/Thompson Sampling
http://www.adaptiveagents.org/mdp?rev=1424649675
This is the model-free reinforcement learning algorithm that we originally used as an example to showcase the Bayesian control rule, inspired by the “Bayesian Q-Learning” paper by Dearden et al. Please cite as: Ortega, P.A. and Braun D.A. “A minimum relative entropy principle for learning and acting”. Journal of Artificial Intelligence Research 38, pp. 475-511, 2010.text/html2015-02-22T18:55:14-04:00peortegaThompson Sampling & Bayesian Control Rule - [Thompson Sampling & Bayesian Control Rule]
http://www.adaptiveagents.org/bayesian_control_rule?rev=1424649314
Thompson sampling is not just a heuristic with nice properties, but, under closer scrutiny, reveals some interesting aspects about the reinforcement learning problem that have not been analyzed before. Two aspects that are particularly interesting are the intimate connection to Bayesian inference (in fact, to adaptive compression) and the intricate relation to causality.text/html2015-02-22T18:44:59-04:00peortegamdp2.png
http://www.adaptiveagents.org/?image=mdp2.png&ns=&rev=1424648699&do=media
<img src="http://www.adaptiveagents.org/_media/mdp2.png?w=500&h=189t=1424648929" alt="mdp2.png" />text/html2015-02-22T17:58:36-04:00peortegamdp1.png
http://www.adaptiveagents.org/?image=mdp1.png&ns=&rev=1424645916&do=media
<img src="http://www.adaptiveagents.org/_media/mdp1.png?w=233&h=375t=1424648699" alt="mdp1.png" />text/html2015-01-23T10:20:57-04:00peortegaboltzmann.jpeg - created
http://www.adaptiveagents.org/?image=boltzmann.jpeg&ns=&rev=1422026457&do=media
<img src="http://www.adaptiveagents.org/_media/boltzmann.jpeg?w=257&h=326t=1422026457" alt="boltzmann.jpeg" />text/html2015-01-15T09:51:29-04:00peortegapapers:bandits_attitude.pdf - created
http://www.adaptiveagents.org/?image=papers%3Abandits_attitude.pdf&ns=papers&rev=1421333489&do=media
text/html2014-11-11T17:59:11-04:00peortegathesis.pdf - created
http://www.adaptiveagents.org/?image=thesis.pdf&ns=&rev=1415746751&do=media
text/html2014-08-25T11:35:15-04:00peortegalella.jpg - created
http://www.adaptiveagents.org/?image=lella.jpg&ns=&rev=1408980915&do=media
<img src="http://www.adaptiveagents.org/_media/lella.jpg?w=500&h=362t=1408980915" alt="lella.jpg" />