X

Download Encoding Robotic Sensor States for Q-Learning PowerPoint Presentation

SlidesFinder-Advertising-Design.jpg

Login   OR  Register
X


Iframe embed code :



Presentation url :

Home / Science & Technology / Science & Technology Presentations / Encoding Robotic Sensor States for Q-Learning PowerPoint Presentation

Encoding Robotic Sensor States for Q-Learning PowerPoint Presentation

Ppt Presentation Embed Code   Zoom Ppt Presentation

PowerPoint is the world's most popular presentation software which can let you create professional Encoding Robotic Sensor States for Q-Learning powerpoint presentation easily and in no time. This helps you give your presentation on Encoding Robotic Sensor States for Q-Learning in a conference, a school lecture, a business proposal, in a webinar and business and professional representations.

The uploader spent his/her valuable time to create this Encoding Robotic Sensor States for Q-Learning powerpoint presentation slides, to share his/her useful content with the world. This ppt presentation uploaded by worldwideweb in Science & Technology ppt presentation category is available for free download,and can be used according to your industries like finance, marketing, education, health and many more.

About This Presentation

Slide 1 - Encoding Robotic Sensor States for Q-Learning using the Self-Organizing Map Gabriel J. Ferrer Department of Computer Science Hendrix College
Slide 2 - Outline Statement of Problem Q-Learning Self-Organizing Maps Experiments Discussion
Slide 3 - Statement of Problem Goal Make robots do what we want Minimize/eliminate programming Proposed Solution: Reinforcement Learning Specify desired behavior using rewards Express rewards in terms of sensor states Use machine learning to induce desired actions Target Platform Lego Mindstorms NXT
Slide 4 - Robotic Platform
Slide 5 - Experimental Task Drive forward Avoid hitting things
Slide 6 - Q-Learning Table of expected rewards (“Q-values”)‏ Indexed by state and action Algorithm steps Calculate state index from sensor values Calculate the reward Update previous Q-value Select and perform an action Q(s,a) = (1 - α) Q(s,a) + α (r + γ max(Q(s',a)))‏
Slide 7 - Certain sensors provide continuous values Sonar Motor encoders Q-Learning requires discrete inputs Group continuous values into discrete “buckets” [Mahadevan and Connell, 1992] Q-Learning produces discrete actions Forward Back-left/Back-right Q-Learning and Robots
Slide 8 - Creating Discrete Inputs Basic approach Discretize continuous values into sets Combine each discretized tuple into a single index Another approach Self-Organizing Map Induces a discretization of continuous values [Touzet 1997] [Smith 2002]
Slide 9 - Self-Organizing Map (SOM)‏ 2D Grid of Output Nodes Each output corresponds to an ideal input value Inputs can be anything with a distance function Activating an Output Present input to the network Output with the closest ideal input is the “winner”
Slide 10 - Applying the SOM Each input is a vector of sensor values Sonar Left/Right Bump Sensors Left/Right Motor Speeds Distance function is sum-of-squared-differences
Slide 11 - SOM Unsupervised Learning Present an input to the network Find the winning output node Update ideal input for winner and neighbors weightij = weightij + (α * (inputij – weightij)) Neighborhood function
Slide 12 - Experiments Implemented in Java (LeJOS 0.85) Each experiment 240 seconds (800 Q-Learning iterations) 36 States Three actions Both motors forward Left motor backward, right motor stopped Left motor stopped, right motor backward
Slide 13 - Rewards Either bump sensor pressed: 0.0 Base reward: 1.0 if both motors are going forward 0.5 otherwise Multiplier: Sonar value greater than 20 cm: 1 Otherwise, (sonar value) / 20
Slide 14 - Parameters Discount (γ): 0.5 Learning rate (α): 1/(1 + (t/100)), t is the current iteration (time step) Used for both SOM and Q-Learning [Smith 2002] Exploration/Exploitation Epsilon = α/4 Probability of random action Selected using weighted distribution
Slide 15 - Experimental Controls Q-Learning without SOM Qa States Current action (1-3) Current bumper states Quantized sonar values (0-19 cm; 20-39; 40+) Qb States Current bumper states Quantized sonar values (9) (0-11 cm…; 84-95; 96+)
Slide 16 - SOM Formulations 36 Output Nodes Category “a”: Length-5 input vectors Motor speeds, bumper values, sonar value Category “b”: Length-3 input vectors Bumper values, sonar value All sensor values normalized to [0-100]
Slide 17 - SOM Formulations QSOM Based on [Smith 2002] Gaussian Neighborhood Neighborhood size is one-half SOM width QT Based on [Touzet 1997] Learning rate is fixed at 0.9 Neighborhood is immediate Manhattan neighbors Neighbor learning rate is 0.4
Slide 18 - Quantitative Results
Slide 19 - Qualitative Results QSOMa Motor speeds ranged from 2% to 50% Sonar values stuck between 90% and 94% QSOMb Sonar values range from 40% to 95% Best two runs arguably the best of the bunch Very smooth SOM values in both cases
Slide 20 - Qualitative Results QTa Sonar values ranged from 10% to 100% Still a weak performer on average Best performer similar to QTb QTb Developed bump-sensor oriented behavior Made little use of sonar Highly uneven SOM values in both cases
Slide 21 - Experimental Area
Slide 22 - First Movie QSOMb Strong performer (Reward: 661.89) Minimum sonar value: 43.35% (110 cm)
Slide 23 - Second Movie Also QSOMb Typical bad performer (Reward: 451.6) Learns to avoid by always driving backwards Baseline “not-forward” reward: 400.0 Minimum sonar value: 57.51% (146 cm) Hindered by small filming area
Slide 24 - Discussion Use of SOM on NXT can be effective More research needed to address shortcomings Heterogeneity of sensors is a problem Need to try NXT experiments with multiple sonars Previous work involved homogeneous sensors Approachable by undergraduate students Technique taught in junior/senior AI course
 

Frequently Asked Questions

> About SlidesFinder?

Slidesfinder is a website that allows users to upload and share their PowerPoint presentations online. It provides a platform for individuals and businesses to share their ideas and knowledge through presentations, and for others to view and download these presentations for educational or professional purposes.
Slidesfinder offers a wide range of presentation topics and categories, including business, education, science, technology, health, and more. Users can also search for presentations using keywords, tags, or by category. The website provides tools to create professional presentations with rich media, animations, and graphics.



One of the key features of Slidesfinder is its user-friendly interface, which allows users to easily upload, view, and share presentations. Users can also embed their presentations in their websites or blogs using the website's embed code feature.
Slidesfinder also offers premium services, such as the ability to create private presentations and to download presentations in high-quality formats. However, the basic features of Slidesfinder are free to use, making it accessible to anyone who wants to share their ideas and knowledge through presentations.

> How do I register with SlidesFinder?

Go to registration page (you can see signup link on top of website page) https://www.slidesfinder.com/signup . If you have facebook/gmail account them just click on SIGN IN WITH FACEBOOK OR SIGN IN WITH GOOGLE button, by this you will be a registered member of slidesfinder without filling any form, required detail automatically will be fatch from your account. If you do not a Facebook account, then click on "Signup". Fill all required fields and you will be a registered member of slidesfinder.

> Is slidesfinder account confirmation is mandatory?

Yes it is mandetory to active your account to login.

> Do I need to signup/login on SlidesFinder before uploading a PowerPoint presentation?

Yes, you need to login with your account before uploading presentation. Your username will be displayed on your uploaded presentation. Your registered email id is needed for sending your stats of uploaded presentation.

Slidesfinder is a sharing website for PowerPoint presentations search and share. Find your interest in the form of powerpoint presentations on slidesfinder and save your valuable time . On Slidesfinder you get presentations from our huge library of professional ppt presentations. We believe in making your search INFORMATIVE and FUN. Find your best ppt presentation from a pool of PowerPoint presentations stacked under important industry categories like business & management, heath & Wellness,eduction & training etc. We provide unique informative PowerPoint presentation for marketers, presenters and educationists. These professional PowerPoint presentations are uploaded by professionals from across numerous industry segments.These ppt presentations are available for FREE download.

Not just finding your interest, but facilitate you broadcast your interest. We have created this platform for easy sharing of PowerPoint presentations, ensuring that these presentations get maximum exposure. Create your slidesfinder account and upload PowerPoint presentations for free, share on social media platforms and BUILD YOUR CROWD WITH PRESENTATION !!

The Great Buddha says, "Share your knowledge.It’s a way to achieve immortality"! So, start sharing knowledge and we are here to make that immortal !!

© 2013-2024 SlidesFinder. All rights reserved.

Re-productivity of content are not allowed. Without prior written permission from author, commercial use of any content is illegal.