tufts web

55 %
45 %
Information about tufts web
Entertainment

Published on November 19, 2007

Author: Columbia

Source: authorstream.com

Learning from how dogs learn:  Learning from how dogs learn Prof. Bruce Blumberg The Media Lab, MIT bruce@media.mit.edu www.media.mit.edu/~bruce About me…:  About me… About me…:  About me… Practical & compelling real-time learning:  Practical & compelling real-time learning Easy for interactive characters to learn what they ought to be able to learn Easy for a human trainer to guide learning process A compelling user experience Provide heuristics and practical design principles My bias & focus:  My bias & focus Learning occurs within an innate structure that biases… Attention Motivation Innate frequency, form and organization of behavior When certain things are most easily learned What are the catalytic components of the scaffolding that make learning possible? sheep|dog:trial by eire:  sheep|dog:trial by eire See sheep|dog video on my website Object persistence:  Object persistence See object persistence video on my website Temporal representation:  Temporal representation See temporal representation (aka Goatzilla) video on my website Alpha Wolf:  Alpha Wolf See alpha wolf video on my website Rover@home:  Rover@home See rover@home video on my website or go to Scientific American Frontiers website Dobie T. Coyote Goes to School:  Dobie T. Coyote Goes to School See Dobie video on my website Why look at Dog Training?:  Why look at Dog Training? Interactive characters pose unique challenges: State, action and state-action spaces are often continuous and far too big to search exhaustively To be compelling characters must Learn “obvious” contingencies between state, actions and consequences quickly Easy to train without visibility into internal state of character. Learning is only one thing they have to do. Dogs and their trainers seem to solve these problems easily Invaluable resources:  Invaluable resources Doing it, and talking to people who do it. Wilkes, Pryor, Ramirez Lindsay, Burch & Bailey, Mackintosh Lorenz, Leyhausen, Coppinger & Coppinger The problem facing dogs (real and synthetic):  The problem facing dogs (real and synthetic) Set of all possible actions Set of all motivational goals Set of all possible stimuli What do I do, when, in order to best satisfy my motivational goals? The space of possible stimuli is wicked big:  The space of possible stimuli is wicked big Time of Occurence State Space The space of possible actions is also very big:  The space of possible actions is also very big Set of all possible actions Action Time of Performance Action Space Who gets credit for good things happening?:  Who gets credit for good things happening? Yumm.. Action Figure -8 Shake High -5 Beg Down Left ear twitch Modality of Stimuli Who gets credit for good things happening?:  Who gets credit for good things happening? Yumm.. Time Conventional idea: back propagation from goal:  Conventional idea: back propagation from goal stalk grab-bite eye orient kill-bite chase Yumm.. Time Credit flows backward Conventional idea: back propagation from goal:  Conventional idea: back propagation from goal stalk grab-bite eye orient kill-bite chase Yumm.. Time Credit flows backward Conventional idea: back propagation from goal:  Conventional idea: back propagation from goal stalk grab-bite eye orient kill-bite chase Yumm.. Time Credit flows backward The problem:  The problem If each element in sequence has 3 variants, there are 729 possible combinations of which 1 may work (ignoring stimuli) If there are 12 possible stimuli, there are 1,586,874,322,944 possible combinations of stimuli-action pairs to explore. Don’t know if it is the right sequence until goal is reached What happens if “variant” needs to be learned? Leyhausen’s suggestion…:  Leyhausen’s suggestion… stalk grab-bite eye orient kill-bite chase Time Each element is innately self-motivating and has innate reward metric motivation & reward motivation & reward motivation & reward motivation & reward motivation & reward motivation & reward Leyhausen’s suggestion…:  Leyhausen’s suggestion… stalk grab-bite eye orient kill-bite chase Time Each element is innately self-motivating and has innate reward metric motivation & reward motivation & reward motivation & reward motivation & reward motivation & reward motivation & reward Coppinger’s suggestion…:  Coppinger’s suggestion… stalk grab-bite eye orient kill-bite chase Time Varying innate tendency to follow behavior with “next” in sequence Functional goal plays incidental role:  Functional goal plays incidental role stalk grab-bite eye orient kill-bite chase Time Propagated value from functional goal plays incidental role Yumm.. Big idea: innate biases make learning possible :  Big idea: innate biases make learning possible Biases include… Temporal Proximity implies causality Attend more readily to certain classes of stimuli than to others (motion vs. speech) Lazy discovery (pay attention once you have a reason to pay attention) Elements may be “innately” self-motivating and have local metric of “goodness” Good trainers actively guide dog’s exploration:  Good trainers actively guide dog’s exploration Behavioral Train behavior, then cue Differential rewards encourage variability Motor Shaping Rewarding successive approximations Luring Pose, e.g. “down” Trajectory, e.g. “figure-8” Dogs constrain search for causal agents:  Dogs constrain search for causal agents Time Consequences Window: Trainer “clicks” signaling reward is coming. When reward is actually received Attention Window: Cue given immediately before or as dog is moving into desired pose Sit Approach Eat Dogs make the problem tractable by constraining search for causal agents to narrow temporal windows Dogs use implicit feedback to guide perceptual learning:  Dogs use implicit feedback to guide perceptual learning Sit Time “sit-utterance” perceived. Approach Eat “click” perceived. Dog decides to sit Build & update perceptual model of “sit-utterance” Dogs use rewarded action to identify potentially promising state to explore and to guide formation of perceptual models Dogs give credit where credit is due…:  Dogs give credit where credit is due… Trainer repeatedly lures dog through a trajectory or into a pose Eventually, dog performs behavior spontaneously Implication Dog associates reward with resulting body configuration or trajectory and not just with “follow-your nose” Observation: dogs give credit where credit is due:  Observation: dogs give credit where credit is due Sit Time “sit-utterance” perceived. Approach Eat “click” perceived. Dog decides to sit Credit sitting in presence of “sit-utterance” Build & update perceptual model of “sit-utterance” D.L.: Take Advantage of Predictable Regularities:  D.L.: Take Advantage of Predictable Regularities Constrain search for causal agents by taking advantage of temporal proximity & natural hierarchy of state spaces Use consequences to bias choice of action But vary performance and attend to differences Explore state and action spaces on “as-needed” basis Build models on demand D.L.: Make Use of All Feedback: Explicit & Implicit:  D.L.: Make Use of All Feedback: Explicit & Implicit Use rewarded action as context for identifying Promising state space and action space to explore Good examples from which to construct perceptual models, e.g., A good example of a “sit-utterance” is one that occurs within the context of a rewarded Sit. D.L.: Make Them Easy to Train:  D.L.: Make Them Easy to Train Respond quickly to “obvious” contingencies Support Luring and Shaping Techniques to prompt infrequently expressed or novel motor actions “Trainer friendly” credit assignment Assign credit to candidate that matches trainer’s expectation The System:  The System Dobie T. Coyote…:  Dobie T. Coyote… See dobie video on my website Limitations and Future Work:  Limitations and Future Work Important extensions Other kinds of learning (e.g., social or spatial) Generalization Sequences Expectation-based emotion system How will the system scale? Useful Insights:  Useful Insights Use Temporal proximity to limit search. Hierarchical representations of state, action and state-action space & use implicit feedback to guide exploration “trainer friendly” credit assignment Luring and shaping are essential Acknowledgements:  Acknowledgements Members of the Synthetic Characters Group, past, present & future Gary Wilkes Funded by the Digital Life Consortium

Add a comment

Related presentations

Related pages

Tufts University

Tufts is recognized as a premier university dedicated to educating new leaders for a changing world. Superb teaching and world-class research equip ...
Read more

Gayle Tufts: Steckbrief, Bilder und News - web.de

Alle Informationen über Gayle Tufts: Alle News, alle Bilder & der Steckbrief (Alter, Größe) - das große Star-Profil von ★ Gayle Tufts ★ auf WEB.DE.
Read more

Tufts Health Plan - Health Insurance in MA and RI

Choose from over 50 affordable health care plans from Tufts Health Plan and compare health insurance for individuals, families, and employers in MA and RI.
Read more

WebEx conferencing tool

Hier sollte eine Beschreibung angezeigt werden, diese Seite lässt dies jedoch nicht zu.
Read more

Microsoft Exchange Email | Tufts Technology Services

Tufts University's email service is Microsoft ... Microsoft Exchange Email. Service ... Access from any Internet-connected device via Outlook Web App;
Read more

Information for Healthcare Providers | Tufts Health Plan

Health insurance reimbursement tools and resources to help physicians, doctors, and providers save time and expedite processing
Read more

Perseus Digital Library

An evolving collection of resources for the study of the ancient world, including archaeology, atlas, texts and translations, text tools and lexica.
Read more

Tufts Technology Services

Tufts Box Your storage-sharing-collaboration solution is free. LEARN MORE. Featured Products. ... Email it@tufts.edu. Contact Tufts Technology Services.
Read more

Tufts University · Tufts Admissions

The Tufts University Undergraduate Admissions site. Keeping the college search interesting.
Read more

sites.tufts.edu - Tufts Self-Serve Blogs and Websites.

Last year I went on medical leave for a semester and thought heavily about how I would feel being back at Tufts. I assumed that because of how bored and ...
Read more