Value and Policy Iterations in Optimal Control and Adaptive Dynamic Programming.
Dimitri P. BertsekasPublished in: IEEE Trans. Neural Networks Learn. Syst. (2017)
Keyphrases
- optimal control
- dynamic programming
- infinite horizon
- optimal policy
- actor critic
- control problems
- policy gradient
- stochastic control
- risk sensitive
- feedback control
- average cost
- reinforcement learning
- multistage
- approximate dynamic programming
- finite horizon
- class of nonlinear systems
- optimal control problems
- state space
- markov decision processes
- brownian motion
- partially observable
- control strategy
- knapsack problem
- linear programming
- policy iteration
- partially observable markov decision processes
- finite state
- optimal solution
- adaptive control
- greedy algorithm
- linear quadratic