Extending the Bellman equation for MDPs to continuous actions and cont. time in the discounted case.
Emmanuel RachelsonFrédérick GarciaPatrick FabianiPublished in: ISAIM (2008)
Keyphrases
- markov decision processes
- action space
- decision theoretic planning
- state and action spaces
- partially observable
- optimal policy
- state space
- dynamic programming
- finite horizon
- infinite horizon
- state action
- average reward
- reward function
- action sets
- decision processes
- markov decision process
- finite state
- piecewise linear
- initial state
- average cost
- probabilistic planning
- continuous state spaces
- differential equations
- case based reasoning