On-policy Q-learning for adaptive optimal control.
Sumit Kumar JhaShubhendu BhasinPublished in: ADPRL (2014)
Keyphrases
- optimal control
- actor critic
- reinforcement learning
- infinite horizon
- optimal policy
- dynamic programming
- policy iteration
- rl algorithms
- control strategy
- feedback control
- policy gradient
- stochastic control
- control problems
- risk sensitive
- action selection
- average cost
- class of nonlinear systems
- learning algorithm
- finite horizon
- control law
- brownian motion
- lyapunov function
- function approximation
- markov decision processes
- partially observable
- adaptive control
- optimal control problems
- neural network
- reinforcement learning algorithms
- long run
- stochastic demand
- convergence rate
- mathematical model