Generalized Dual Dynamic Programming for Infinite Horizon Problems in Continuous State and Action Spaces.
Joseph WarringtonPaul N. BeuchatJohn LygerosPublished in: IEEE Trans. Autom. Control. (2019)
Keyphrases
- infinite horizon
- dynamic programming
- dec pomdps
- optimal policy
- optimal control
- finite horizon
- markov decision process
- continuous state and action spaces
- decision problems
- markov decision processes
- state space
- partially observable
- markov decision problems
- long run
- multi agent
- continuous state
- multistage
- search algorithm
- reinforcement learning
- decision making