A Learning Algorithm for Risk-Sensitive Cost
Material type:
TextPublication details: Bangalore: Department of Mathematics, Indian Institute of Science: 2006Description: A linear function approximation based reinforcement learning algorithm is proposed for Markov decision processes with infinite horizon risk-sensitive cost. Its convergence is proved using the ‘o.d.e. method’ for stochastic approximation. The scheme is alsISBN: - NULL
| Item type | Current library | Home library | Collection | Call number | Status | Barcode | |
|---|---|---|---|---|---|---|---|
Pre-Prints
|
MATH-LiB General Stack | MATH-LiB | NFIC | MathPP25 (Browse shelf(Opens below)) | Not for loan | MathPP25 |
Total holds: 0
There are no comments on this title.
Log in to your account to post a comment.