Prepared Questions for Speakers Robot Learning Workshop, NeurIPS 2019
This form is for gathering proposed questions for each of the speakers (see some examples below). The organizers will review all submissions, and select one question per speaker. If your question is selected (we will notify you via email), you will have the opportunity to ask the question at the end of the speaker's presentation. Audience Q&A will proceed immediately following this question. You are welcome to submit questions for multiple speakers by filling out the form multiple times. By submitting a question, you are helping to foster thoughtful discussion in the workshop - thank you!

Deadline for submission: Wednesday, December 11th

*Examples of challenge questions from NeurIPS 2017 HRL Workshop (https://bit.ly/2IZCfq5)*
[Josh Achiam] Works like Feudal Networks and Option-Critic make claims of beating non-hierarchical baselines in several settings. Anecdotally, wins for hierarchy seem hard to reproduce
Is the current research in deep HRL rigorous enough / reproducible enough to justify existing claims? If not, what steps forward do we have to take?

[Karol Hausman] You have done a lot of original work on policy gradients, actor-critic methods, and in general, reinforcement learning in robotics. These days, we see a lot of these methods that achieve impressive results (although mostly in simulation) using different versions of these methods with deep neural networks.
Do you see any breakthroughs in the most recent deep RL methods that are beyond applying a better function approximator to the already known methods? If so, what are those?
What do you think are the most exciting research directions that opened up with
the arrival of deep reinforcement learning methods?
Email address *
Next
Never submit passwords through Google Forms.
This content is neither created nor endorsed by Google. Report Abuse - Terms of Service - Privacy Policy