Building efficient partial plans using Markov decision processes.
Pierre LarochePublished in: ICTAI (2000)
Keyphrases
- markov decision processes
- state space
- optimal policy
- reinforcement learning
- dynamic programming
- finite state
- decision theoretic planning
- transition matrices
- policy iteration
- partially observable
- markov decision process
- bayesian networks
- reward function
- average reward
- partial plans
- sufficient conditions
- least squares
- search space