[AI Seminar] AI Seminar sponsored by Apple -- David Abel (Brown) -- October 31
vitercik at cs.cmu.edu
Sun Oct 29 12:01:38 EDT 2017
I've attached a schedule for David's visit. Please sign up for a slot if
you would like to meet with him.
On Sun, Oct 29, 2017 at 2:13 AM, Adams Wei Yu <weiyu at cs.cmu.edu> wrote:
> Dear faculty and students,
> We look forward to seeing you next Tuesday, October 31, at noon in NSH
> 3305 for AI Seminar sponsored by Apple. To learn more about the seminar
> series, please visit the AI Seminar webpage
> On Tuesday, David Abel <https://cs.brown.edu/~dabel/> from Brown
> University will give the following talk:
> Title: Abstraction and Lifelong Reinforcement Learning
> Lifelong Reinforcement Learning (RL) presents a diversity of challenges.
> Agents must effectively transfer knowledge across tasks while
> simultaneously addressing exploration, credit assignment, and
> generalization. Abstraction can help overcome these hurdles by compressing
> the state space or empowering the action space of a learning agent, thereby
> reducing the computational and statistical burdens of learning. In this
> talk, I summarize our new results on the effect of abstractions on lifelong
> RL. First, we introduce a new class of value-preserving state abstractions
> whose optimal form can be computed efficiently, improving over existing
> NP-Hardness results. Second, we provide a generic sample bound for
> computing high confidence state abstractions in the lifelong setting.
> Third, we show experimentally that state abstractions only offer marginal
> improvements to lifelong learning on their own, but when paired with action
> abstraction, can enable efficient learning. Further, joint state-action
> abstractions induce a closed operator on representations, thereby yielding
> a simple recipe for constructing and analyzing hierarchies for RL.
-------------- next part --------------
An HTML attachment was scrubbed...
More information about the ai-seminar-announce