Features
Solves discrete-time Markov Decision Problems using dynamic programming
Solves finite and infinite time problems
Uses either function or policy iteration for infinite horizon problems
Solves discounted and average return problems
Solves models with different stages
Solves problems with partial observability and model uncertainty (adaptive management)
Includes procedures for working with both explicit and implicit spatial models
State transitions can be expressed in terms of transition matrices or as functions
Interpolation over rectangular grids and simplex grids
Flexible input structure facilitates ease of use and efficient operation
Bayesian Influence Diagram approach to model specification is available
Includes tools for simulation, long-run analysis and graphic displays
60+ page User’s Guide
It’s free!
Adelgid infestation