[Ml-stat-talks] Sainbayar Sukhbaatar: Friday, March 17th from 12:30 to 1:30pm in COS 105
bee at princeton.edu
Tue Mar 14 20:01:33 EDT 2017
Talk of interest for Friday, March 17th from 12:30 to 1:30pm in COS 105.
Interesting especially to people who work with machine learning, deep
learning, and reinforcement learning.
Title: Intrinsic Motivation and Automatic Curricula via Asymmetric Self-Play
We describe a simple scheme that allows an agent to explore its environment
in an unsupervised manner. Our scheme pits two versions of the same agent,
Alice and Bob, against one another. Alice proposes a task for Bob to
complete; and then Bob attempts to complete the task. In this work we will
focus on (nearly) reversible environments, or environments that can be
reset, and Alice will ``propose'' the task by running a set of actions and
then Bob must partially undo, or repeat them, respectively. Via an
appropriate reward structure, Alice and Bob automatically generate a
curriculum of exploration, enabling unsupervised training of the agent.
When deployed on an RL task within the environment, this unsupervised
training reduces the number of episodes needed to learn.
Sainbayer is a PhD student at NYU working with Rob Fergus and Yann LeCun.
-------------- next part --------------
An HTML attachment was scrubbed...
More information about the Ml-stat-talks