Download presentation
Presentation is loading. Please wait.
Published byBrian Henderson Modified over 9 years ago
1
Introduction to Reinforcement Learning Hiren Adesara Prof: Dr. Gittens
2
Sources for this presentation Lecture videos of – Mr. Satinder Singh, University of Michigan. – Douglas Aberdeen, Australian National University. From www.videolectures.net Book : Introduction to Reinforcement Learning by Sutton and Barto (http://www.cs.ualberta.ca/%7Esutton/book/ ebook/the-book.html)
4
Observation-Action-Response. O 1 a 1 r 1 o 2 a 2 r 2 o 3 a 3 r 3 Agent chooses action so as to maximize expected cumulative reward over time. Observations can be vectors or other structures. Actions are multi-dimensional. Rewards are scalar. (known or unknown). Agents have partial knowledge about environment. Another View of RL
5
Demo..
7
RL and Machine Learning Supervised Learning – Learning approach to regression and classification. – Learning from example and learning from teacher. Unsupervised learning – Learning approaches to dimensionality reduction, density estimation and recording data based on some principles. Reinforcement Learning – Learning approaches to sequential decision making. – Learning from critics, learning from delayed reward.
8
Key ideas of RL Markov Decision Process(MDP). Temporal Differences( updating a guess on the basis of the previous guess). Functional approximation.
9
Markov Decision Process
10
N
11
Temporal Differences
15
Questions ????
Similar presentations
© 2025 SlidePlayer.com. Inc.
All rights reserved.