Computing Factored Value Functions for Policies in Structured MDPs.
Daphne KollerRonald ParrPublished in: IJCAI (1999)
Keyphrases
- optimal policy
- state space
- markov decision processes
- factored markov decision processes
- markov decision problems
- markov decision process
- reinforcement learning
- reward function
- algebraic decision diagrams
- factored mdps
- finite horizon
- average cost
- basis functions
- multistage
- decision diagrams
- policy search
- state variables
- policy iteration
- control policies
- structured data
- decision theoretic planning
- linear programming
- approximate policy iteration
- dynamic programming
- real world