QuickTopic (SM) free message boards QuickTopic (SM) free message boards
Skip to Messages
  Sign In to access your topic list  |New Topic |My Topics|Profile
Upgrade to Pro   Customize, show pictures, add an intro, and more:   QuickTopic Pro...and check out QuickThreadSM
Topic: Policy invariance under reward transformations: ... reward shaping
Views: 354, Unique: 196 
Subscribers: 0
What's
this?
Printer-Friendly Page
Subscribe to get & post, or stop messages by email Subscribe
All messages    << 18-31  17-17 of 31  1-16 >>
About these ads
Who | When
Messagessort recent-top   
Post a new message
 
Yohan Kim  17
04-09-2002 04:47 PM ET (US)
(in response to message #15)
My understanding of the role of potential function in Q-function is lacking in some parts. However, for the sake of class participation and also of letting others know of my concerns I would like to state what I think I know.

I also think that using function of the form
F(s,a,s')=phi(s')-phi(s) to make one circular transition from state s1,s2,..sn, and finally to itself will result in a total F of zero. However when F() is used in the optimal Q-function, presence of the gamma factor makes value of F() time dependent.
RSS link What's this?
All messages    << 18-31  17-17 of 31  1-16 >>
QuickTopicSM message boards
Over 200,000 topics served
Learn more Frequently asked questions  Acknowledgements
What they're saying about QuickTopic
 Questions, comments, or suggestions? Contact Us
Read our use policy before beginning. We value your privacy; please read our privacy statement.
Copyright ©1999-2008 Internicity Inc. All rights reserved.