[Colloquium] REMINDER: 2/14 Talks at TTIC: Josiah Hanna, UT Austin

[Mary Marre via Colloquium]

*When:     Thursday, February 14th at 11:00 am*

Where:    TTIC, 6045 S Kenwood Avenue, 5th Floor, Room 526

Who:      Josiah Hanna, UT Austin


*Title:*       Data Efficient Reinforcement learning for Autonomous Robots
with Simulated and Off-policy Data

*Abstract:*
Learning from interaction with the environment -- trying untested actions,
observing successes and failures, and tying effects back to causes -- is
one of the first capabilities thought of when considering intelligent
agents. Reinforcement learning is the area of artificial intelligence
research that has the goal of allowing autonomous agents to learn in this
way. Despite many recent empirical successes, most modern reinforcement
learning algorithms are still limited by the large amounts of experience
required before useful skills are learned. Making reinforcement learning
more data efficient would allow computers to autonomously solve complex
tasks in dynamic environments such as those found in robotics, traffic
management, or healthcare.

My research focuses on giving agents the ability to predict how their
actions influence their ability to solve a given task. In this talk, I will
describe my research in this area and how efficient prediction connects to
efficient reinforcement learning. In the first part of the talk, I will
introduce an algorithm that allows an agent to find informative exploratory
behaviors for learning how it’s actions influence task performance. In the
second part of the talk, I will introduce an algorithm that allows robot
skills learned in simulated environments to transfer to the real world.
Finally, I will describe directions for future work that will lead to an
increased applicability of reinforcement learning to real world problems.

*Bio:*
Josiah Hanna is a PhD candidate in the computer science department at the
University of Texas at Austin advised by Professor Peter Stone. Prior to
attending UT Austin, he completed his bachelors degree in computer science
and mathematics at the University of Kentucky advised by Professor Judy
Goldsmith. During the summer of 2017, he completed a research internship at
Google. Josiah is an NSF Graduate Research Fellow and an IBM PhD Fellow.


*Host: *Matthew Walter <mwalter at ttic.edu>


Mary C. Marre
Administrative Assistant
*Toyota Technological Institute*
*6045 S. Kenwood Avenue*
*Room 517*
*Chicago, IL  60637*
*p:(773) 834-1757*
*f: (773) 357-6970*
*mmarre at ttic.edu <mmarre at ttic.edu>*


On Wed, Feb 13, 2019 at 5:18 PM Mary Marre <mmarre at ttic.edu> wrote:

> *When:     Thursday, February 14th at 11:00 am*
>
> Where:    TTIC, 6045 S Kenwood Avenue, 5th Floor, Room 526
>
> Who:      Josiah Hanna, UT Austin
>
>
> *Title:*       Data Efficient Reinforcement learning for Autonomous
> Robots with Simulated and Off-policy Data
>
> *Abstract:*
> Learning from interaction with the environment -- trying untested actions,
> observing successes and failures, and tying effects back to causes -- is
> one of the first capabilities thought of when considering intelligent
> agents. Reinforcement learning is the area of artificial intelligence
> research that has the goal of allowing autonomous agents to learn in this
> way. Despite many recent empirical successes, most modern reinforcement
> learning algorithms are still limited by the large amounts of experience
> required before useful skills are learned. Making reinforcement learning
> more data efficient would allow computers to autonomously solve complex
> tasks in dynamic environments such as those found in robotics, traffic
> management, or healthcare.
>
> My research focuses on giving agents the ability to predict how their
> actions influence their ability to solve a given task. In this talk, I will
> describe my research in this area and how efficient prediction connects to
> efficient reinforcement learning. In the first part of the talk, I will
> introduce an algorithm that allows an agent to find informative exploratory
> behaviors for learning how it’s actions influence task performance. In the
> second part of the talk, I will introduce an algorithm that allows robot
> skills learned in simulated environments to transfer to the real world.
> Finally, I will describe directions for future work that will lead to an
> increased applicability of reinforcement learning to real world problems.
>
> *Bio:*
> Josiah Hanna is a PhD candidate in the computer science department at the
> University of Texas at Austin advised by Professor Peter Stone. Prior to
> attending UT Austin, he completed his bachelors degree in computer science
> and mathematics at the University of Kentucky advised by Professor Judy
> Goldsmith. During the summer of 2017, he completed a research internship at
> Google. Josiah is an NSF Graduate Research Fellow and an IBM PhD Fellow.
>
>
> *Host: *Matthew Walter <mwalter at ttic.edu>
>
>
>
>
> Mary C. Marre
> Administrative Assistant
> *Toyota Technological Institute*
> *6045 S. Kenwood Avenue*
> *Room 517*
> *Chicago, IL  60637*
> *p:(773) 834-1757*
> *f: (773) 357-6970*
> *mmarre at ttic.edu <mmarre at ttic.edu>*
>
>
> On Fri, Feb 8, 2019 at 10:36 AM Mary Marre <mmarre at ttic.edu> wrote:
>
>> *When:     Thursday, February 14th at 11:00 am*
>>
>> Where:    TTIC, 6045 S Kenwood Avenue, 5th Floor, Room 526
>>
>> Who:      Josiah Hanna, UT Austin
>>
>>
>> *Title:*       Data Efficient Reinforcement learning for Autonomous
>> Robots with Simulated and Off-policy Data
>>
>> *Abstract:*
>> Learning from interaction with the environment -- trying untested
>> actions, observing successes and failures, and tying effects back to causes
>> -- is one of the first capabilities thought of when considering intelligent
>> agents. Reinforcement learning is the area of artificial intelligence
>> research that has the goal of allowing autonomous agents to learn in this
>> way. Despite many recent empirical successes, most modern reinforcement
>> learning algorithms are still limited by the large amounts of experience
>> required before useful skills are learned. Making reinforcement learning
>> more data efficient would allow computers to autonomously solve complex
>> tasks in dynamic environments such as those found in robotics, traffic
>> management, or healthcare.
>>
>> My research focuses on giving agents the ability to predict how their
>> actions influence their ability to solve a given task. In this talk, I will
>> describe my research in this area and how efficient prediction connects to
>> efficient reinforcement learning. In the first part of the talk, I will
>> introduce an algorithm that allows an agent to find informative exploratory
>> behaviors for learning how it’s actions influence task performance. In the
>> second part of the talk, I will introduce an algorithm that allows robot
>> skills learned in simulated environments to transfer to the real world.
>> Finally, I will describe directions for future work that will lead to an
>> increased applicability of reinforcement learning to real world problems.
>>
>> *Bio:*
>> Josiah Hanna is a PhD candidate in the computer science department at the
>> University of Texas at Austin advised by Professor Peter Stone. Prior to
>> attending UT Austin, he completed his bachelors degree in computer science
>> and mathematics at the University of Kentucky advised by Professor Judy
>> Goldsmith. During the summer of 2017, he completed a research internship at
>> Google. Josiah is an NSF Graduate Research Fellow and an IBM PhD Fellow.
>>
>>
>> *Host: *Matthew Walter <mwalter at ttic.edu>
>>
>> Mary C. Marre
>> Administrative Assistant
>> *Toyota Technological Institute*
>> *6045 S. Kenwood Avenue*
>> *Room 517*
>> *Chicago, IL  60637*
>> *p:(773) 834-1757*
>> *f: (773) 357-6970*
>> *mmarre at ttic.edu <mmarre at ttic.edu>*
>>
>>
>>
>>>
>>>
>>> Mary C. Marre
>>> Administrative Assistant
>>> *Toyota Technological Institute*
>>> *6045 S. Kenwood Avenue*
>>> *Room 517*
>>> *Chicago, IL  60637*
>>> *p:(773) 834-1757*
>>> *f: (773) 357-6970*
>>> *mmarre at ttic.edu <mmarre at ttic.edu>*
>>>
>>
-------------- next part --------------
An HTML attachment was scrubbed...
URL: <http://mailman.cs.uchicago.edu/pipermail/colloquium/attachments/20190214/5fa3f548/attachment-0001.html>