Differences

This shows you the differences between two versions of the page.

Link to this comparison view

Both sides previous revision Previous revision
Next revision
Previous revision
sesiuni:basics-of-reinforcement-learning [2018/08/14 20:01]
amacovei
sesiuni:basics-of-reinforcement-learning [2018/09/01 01:43] (current)
amacovei
Line 1: Line 1:
 == Basics of Reinforcement Learning == == Basics of Reinforcement Learning ==
  
-Mentor: Ioana Veronica Chelu[[ioana.chelu28@gmail.com|email]].+Mentor: Ioana Veronica Chelu\\ 
 +[[ioana.chelu28@gmail.com|ioana.chelu28@gmail.com]]
  
 == Overview == == Overview ==
  
-Starting from the idea of learning as the basis for intelligence,​ reinforcement learning (RL) has been proposed as the adaptive learning-based algorithm for decision making in animals emphasizing that the elements we encounter in this framework have empirical evidence accumulated from neuroscience studies.\\+Starting from the idea of learning as the basis for intelligence,​ reinforcement learning (RL) has been proposed as the adaptive learning-based algorithm for decision making in animals emphasizing that the elements we encounter in this framework have empirical evidence accumulated from neuroscience studies.\\ \\
 This workshop is concerned with setting RL in the framework of Markov Decision Processes, learning how to obtain goal-directed behavior of an agent by means of pure interaction with an environment. It is mixed with practical examples of learning with it.  This workshop is concerned with setting RL in the framework of Markov Decision Processes, learning how to obtain goal-directed behavior of an agent by means of pure interaction with an environment. It is mixed with practical examples of learning with it. 
 It will also briefly overview some of the recent success stories concerning RL and some research challenges and frontiers in this field of research. It will also briefly overview some of the recent success stories concerning RL and some research challenges and frontiers in this field of research.
Line 14: Line 15:
   - How to scale this framework to high-dimensional input and output spaces, making it more similar to how animals learn.   - How to scale this framework to high-dimensional input and output spaces, making it more similar to how animals learn.
   - Interact with a deep learning framework for function approximation and apply this to the same task of learning from trial and error behavior.   - Interact with a deep learning framework for function approximation and apply this to the same task of learning from trial and error behavior.
 +
 +== Format and Curriculum ==
 +The workshop will be held on 28, 30 and 31 August, at 9:00 AM.
 +
  
 == Tutorials == == Tutorials ==
Line 27: Line 32:
 Intro tensorflow and sonnet: ​ Intro tensorflow and sonnet: ​
 [[https://​github.com/​ioanachelu/​PracticalSessions/​blob/​master/​introductory/​Intro_Tensorflow_and_Sonnet.ipynb|Click]]\\ [[https://​github.com/​ioanachelu/​PracticalSessions/​blob/​master/​introductory/​Intro_Tensorflow_and_Sonnet.ipynb|Click]]\\
 +
 +Special thanks to the organizers, speakers and lab assistants of the TMLSS - Transylvanian Machine Learning Summer School (https://​tmlss.ro/​) for the content of the labs presented during the workshops.\\
 == Registration == == Registration ==
  
 Click [[https://​docs.google.com/​forms/​d/​e/​1FAIpQLSfHr7HkhcZLNFhnrpixsbI7cwiaAKKssnLMI_i0__f945PRFw/​viewform|here]]. Click [[https://​docs.google.com/​forms/​d/​e/​1FAIpQLSfHr7HkhcZLNFhnrpixsbI7cwiaAKKssnLMI_i0__f945PRFw/​viewform|here]].
sesiuni/basics-of-reinforcement-learning.1534266112.txt.gz · Last modified: 2018/08/14 20:01 by amacovei