Handbook of Learning and Approximate Dynamic Progr Amming Book

	Foreword	1
1	ADP : goals, opportunities and principles	3
Pt. I	Overview	45
2	Reinforcement learning and its relationship to supervised learning	47
3	Model-based adaptive critic designs	65
4	Guidance in the use of adaptive critics for control	97
5	Direct neural dynamic programming	125
6	The linear programming approach to approximate dynamic programming	153
7	Reinforcement learning in large, high-dimensional state spaces	179
8	Hierarchical decision making	203
Pt. II	Technical advances	233
9	Improved temporal difference methods with linear function approximation	235
10	Approximate dynamic programming for high-dimensional resource allocation problems	261
11	Hierarchical approaches to concurrency, multiagency, and partial observability	285
12	Learning and optimization - from a system theoretic perspective	311
13	Robust reinforcement learning using integral-quadratic constraints	337
14	Supervised actor-critic reinforcement learning	359
15	BPTT and DAC - a common framework for comparison	381
Pt. III	Applications	405
16	Near-optimal control via reinforcement learning	407
17	Multiobjective control problems by reinforcement learning	433
18	Adaptive critic based neural network for control-constrained agile missile	463
19	Applications of approximate dynamic programming in power systems control	479
20	Robust reinforcement learning for heating, ventilation, and air conditioning control of buildings	517
21	Helicopter flight control using direct neural dynamic programming	535
22	Toward dynamic stochastic optimal power flow	561
23	Control, optimization, security, and self-healing of benchmark power systems	599