On the convergence of successive approximations in dynamic programming with non-zero terminal reward.
Shaler Stidham Jr.Published in: Z. Oper. Research (1981)
Keyphrases
- dynamic programming
- reinforcement learning
- stationary policies
- state space
- linear programming
- initial conditions
- closed form
- convergence rate
- coarse to fine
- global convergence
- stereo matching
- convergence speed
- dynamic programming algorithms
- decision trees
- computationally tractable
- approximation methods
- greedy algorithm
- markov decision processes
- optimal policy
- sufficient conditions
- multi objective
- multi agent systems
- case study