In these talks we consider the problem of planning on probabilistic systems in order to satisfy given properties or optimizing some reward.Back to Start page
Title | Authors | Reference Papers |
---|---|---|
RDDL language description | Scott Sanner | RDDL, Sanner's slides |
Trial-based Heuristic Tree Search for Finite Horizon MDPs | THTS(long version), THTS(short version), PROST paper | |
Gourmand and UCT | UCT/PROST, Gourmand | |
Plannig with first-order TEP goals | J.A. Baier and S. A. McIlraith | paper |