Parallel Optimization of Motion Controllers via Policy Iteration.
Jefferson A. Coelho Jr.R. SitaramanRoderic A. GrupenPublished in: NIPS (1995)
Keyphrases
- policy iteration
- markov decision processes
- reinforcement learning
- model free
- fixed point
- image sequences
- optimization algorithm
- finite state
- sample path
- least squares
- optimal policy
- constrained optimization
- optimal control
- infinite horizon
- linear programming
- artificial neural networks
- moving objects
- state space
- temporal difference
- markov decision process
- dynamic programming
- average reward
- control system