Artificial Intelligence

   

Procrastinative Reinforcement Learning

Authors: Joy Chopra, Sandipan Haldar

We propose using procrastination to prepare the agent for emergency situations and to enable it to learn to finish work in shorter horizons. This can be done by regulating the discount factor or by making the agent explore for most of the episode, and taking exploitationary actions near the end. We will finish the rest of this paper very soon.

Comments: 1 Page.

Download: PDF

Submission history

[v1] 2018-09-27 02:00:51

Unique-IP document downloads: 33 times

Vixra.org is a pre-print repository rather than a journal. Articles hosted may not yet have been verified by peer-review and should be treated as preliminary. In particular, anything that appears to include financial or legal advice or proposed medical treatments should be treated with due caution. Vixra.org will not be responsible for any consequences of actions that result from any form of use of any documents on this website.

Add your own feedback and questions here:
You are equally welcome to be positive or negative about any paper but please be polite. If you are being critical you must mention at least one specific error, otherwise your comment will be deleted as unhelpful.

comments powered by Disqus