Parallel Algorithms for Stochastic Dynamic Programming with Continuous State and Control Variables.
Elizabeth A. EschenbachChristine A. ShoemakerHugh M. CaffeyPublished in: INFORMS J. Comput. (1995)
Keyphrases
- continuous state
- stochastic dynamic programming
- parallel algorithm
- control policies
- reinforcement learning
- finite state
- robot navigation
- state dependent
- action space
- planning problems
- control system
- approximate dynamic programming
- partially observable markov decision processes
- optimal policy
- shared memory
- markov chain
- control policy
- control strategy
- autonomous robots
- markov decision processes
- motion control
- state space
- control strategies
- dynamic programming
- mobile robot
- state action
- model free
- linear program
- influence diagrams
- probabilistic inference