White D.J. — Markov Decision Processes :: Электронная библиотека попечительского совета мехмата МГУ

Главная Ex Libris Книги Журналы Статьи Серии Каталог Wanted Загрузка ХудЛит Справка Поиск по индексам Поиск Форум

Авторизация

Поиск по указателям

White D.J. — Markov Decision Processes

Обсудите книгу на научном форуме

Нашли опечатку?
Выделите ее мышкой и нажмите Ctrl+Enter

Название: Markov Decision Processes

Автор: White D.J.

Аннотация:

An up-to-date, unified and rigorous treatment of theoretical, computational and applied research on Markov decision process models. Concentrates on infinite-horizon discrete-time models. Discusses arbitrary state spaces, finite-horizon and continuous-time discrete-state models. Also covers modified policy iteration, multichain models with average reward criterion and sensitive optimality. Features a wealth of figures which illustrate examples and an extensive bibliography.

Язык:

Рубрика: Математика/Вероятность/Стохастические процессы/

Статус предметного указателя: Готов указатель с номерами страниц

ed2k: ed2k stats

Год издания: 1993

Количество страниц: 224

Добавлена в каталог: 15.06.2005

Операции: Положить на полку | Скопировать ссылку для форума | Скопировать ID

Предметный указатель

Absorbing state      15 31 53 89 110 124 138
action      34 117
Action space      25
Adaptive      130 131 140 157
Aggregation      151
Algorithm      59 87
Approximation      150 154 156 157
Asymptotic      6 14 17 44
Average expected reward per unit time      44 49 76 104 112 121 133
Average probability      9 106 108
Bayesian      130
Bias      7 11 46 52 105
Block simplex      111
Bound      64 117
Burgling      174
Capacity planning      179
Cesaro      9 49
Chronological      1 25 26 40
Column generation      162 165 166
Complementary slackness      109
Constraint      163
Convex      148 158
Cost      25
Cricket      177
Crossing a road      172
Dairy herd      155
Decision epoch      117
Decision interval      118
Decision rule      1 17 26 27 132
Decomposition      151
Defective production      55 115
Deterministic      27 132
Discount      12 26 28 41 44 111 117 159
Dominate      98
Elimination of actions      90 149
Ergodic      7 45
Expected reward between decision epochs      123
Expected state      153
Expected total discounted reward      12 14 26 40 49 59 99 118 147
Expected total reward      1 4 5
Expected total reward to absorption      17 90
Feasible ideal solution      100
Fixed point      41
Gain      7 11 76
history      25 131 132
Horizon      1 25 26 31 33 40 41 53 59 62 76 90 93 99 104 113 118 121 125 133 159
Identity matrix      3 45
Inventory      15 17 33 54 57 115 125 143 147 148 149 152 158 159 181
Isotonicity      148 149
Lagrange      152
Lattice      148
Least element      100 105
Linear programme      98 100 101 105 110 124 161 165 166 167 169 170
Loss of optimality      87
Maintenance      135
Markov      27 33 117
Markov game      167
Maximal element      160 161 162
Measurable      27 163
Minimal element      98 160
moment      166
Monotone      64

Multiple chain      8 45 49
Multiple objective      159
Norm      63
Operator      4 28 36 38 122 133 149 155 156 162
Optimality criteria      27
Optimality equation      46 118 121 132 147
Overhaul      126 171
Oyster farming      173
parametric      149 157 162
Partially observable      130 131 150 153 157
Penalty      25
Perfect solution      100
Piecewise affine      158
Piecewise linear      133
Policy      26
Policy space      46 62 71 75 84 111 117 121 123
Post-optimality      157 158
Posterior probability      132
Prior probability      57 102 130
Production scheduling      151
Quasi order      148
queuing      17 55 1 1 125 130 181
Randomise      34 160 167
Regular      45 51 77
Relative value      80
replacement      171
Reservoir      151
Reward      1 3 25 117 163
river      151
Search      134 138 175
Semi-Markov      116
Sensitivity      157 158
Separable      149 152
Sequential sampling      130 141 142
Shuttle      176
span      67
Spline Function      155
Stabilisation      70
State      1 3 24 25 1 130
Stationary      25 27 33 40 41 44 53 59 89 99 104 110 130
Steady state      9 45 51
Structured policy      147
Successive approximations      62
Sufficient statistic      142
Superharmonic      99 156
Supermodularity      148 149
Tax      182
Taxi cab      50
Terminal value      47 93 114
Termination of algorithm      72
Toymaker      1 14 21 39 52 68 81 82 88 92 103 109
Transient      7 8 45 85 105
Transition probability      1
Uni-chain      7 11 45 104 163
Utility      163
Value function      26 119
Value iteration      62 75 76 119 123 155
Variance      31 56 153 163 165 167
Vector minimum      148
Vector order      162
z-transform      5 117
Zero-sum game      168

О проекте