en-de
en-es
en-fr
en-sl
en
en-zh
0.25
0.5
0.75
1.25
1.5
1.75
2
A Non-Parametric Approach to Dynamic Programming
Published on Jan 25, 20124249 Views
In this paper, we consider the problem of policy evaluation for continuous-state systems. We present a non-parametric approach to policy evaluation, which uses kernel density estimation to represent t
Related categories
Chapter list
A Non-Parametric Approach to Dynamic Programming00:00
Motivation00:19
Outline - 100:51
Reinforcement Learning - 100:57
Reinforcement Learning - 201:09
Reinforcement Learning - 301:17
Reinforcement Learning - 401:28
Reinforcement Learning - 501:49
Reinforcement Learning - 601:53
Value Functions - 102:05
Value Functions - 202:16
Value Functions - 302:34
Value Functions - 402:48
Value Functions - 502:57
Value Functions - 603:27
Value Functions - 703:37
Value Functions - 803:53
Value Functions - 904:19
Reinforcement Learning Approaches - 104:32
Reinforcement Learning Approaches - 204:39
Reinforcement Learning Approaches - 304:55
Reinforcement Learning Approaches - 405:10
Reinforcement Learning Approaches - 505:37
Value Function Methods - 105:41
Value Function Methods - 205:51
Value Function Methods - 306:10
Value Function Methods - 406:16
Value Function Methods - 506:26
Value Function Methods - 606:33
Value Function Methods - 706:39
Reinforcement Learning Approaches06:54
Discrete State Dynamic Programming - 107:02
Discrete State Dynamic Programming - 207:43
Discrete State Dynamic Programming - 307:56
Linear-Quadratic Optimal Control - 108:01
Linear-Quadratic Optimal Control - 208:28
Linear-Quadratic Optimal Control - 308:37
Outline - 208:44
Non-Parametric Dynamic Programming - 109:17
Non-Parametric Dynamic Programming - 209:30
NPDP System Model - 109:53
NPDP System Model - 210:38
NPDP Form of Value Function - 111:01
NPDP Form of Value Function - 211:16
NPDP Form of Value Function - 311:32
NPDP Form of Value Function - 411:49
NPDP Policy Evaluation - 112:09
NPDP Policy Evaluation - 212:26
Algorithm Overview13:03
Outline - 313:58
Numerical Evaluation14:08
Value Function15:08
100 Samples Evaluation15:22
200 Samples Evaluation15:40
300 Samples Evaluation15:50
Discussion15:56
Conclusion16:34