Computer Science – Artificial Intelligence
Scientific paper
2011-07-27
Proc. 22nd International Conf. on Algorithmic Learning Theory (ALT-2011) pages 383-397
Computer Science
Artificial Intelligence
17 LaTeX pages, 5 figures
Scientific paper
A possibly immortal agent tries to maximise its summed discounted rewards over time, where discounting is used to avoid infinite utilities and encourage the agent to value current rewards more than future ones. Some commonly used discount functions lead to time-inconsistent behavior where the agent changes its plan over time. These inconsistencies can lead to very poor behavior. We generalise the usual discounted utility model to one where the discount function changes with the age of the agent. We then give a simple characterisation of time-(in)consistent discount functions and show the existence of a rational policy for an agent that knows its discount function is time-inconsistent.
Hutter Marcus
Lattimore Tor
No associations
LandOfFree
Time Consistent Discounting does not yet have a rating. At this time, there are no reviews or comments for this scientific paper.
If you have personal experience with Time Consistent Discounting, we encourage you to share that experience with our LandOfFree.com community. Your opinion is very important and Time Consistent Discounting will most certainly appreciate the feedback.
Profile ID: LFWR-SCP-O-113670