Year: 2025
Type: preprint
Abstract: We consider a general aggregation framework for discounted finite-state infinite horizon dynamic programming (DP) problems. It defines an aggregate problem whose optimal cost function can be obtained off-line by exact DP and then used as a terminal cost approximation for an on-line reinforcement learning (RL) scheme. We derive a bound on the error between the optimal cost functions of the aggregate problem and the original problem. This bound was first derived by Tsitsiklis and van Roy [TvR96] for the special case of hard aggregation. Our bound is similar but applies far more broadly, including to soft aggregation and feature-based aggregation schemes.
Source: arXiv (Cornell University)
Authors: Li, Yuchao, Bertsekas, Dimitri
Language: English
Subfield: Artificial Intelligence
Field: Computer Science
Domain: Physical Sciences
Open Access status: green
OpenAlex ID: W4417182767
Cites:
Cited by:
Related to: