en-de
en-es
en-fr
en-sl
en
en-zh
0.25
0.5
0.75
1.25
1.5
1.75
2
Reinforcement Learning
Published on Feb 25, 20077220 Views
Reinforcement learning is about learning good control policies given only weak performance feedback: occasional scalar rewards that might be delayed from the events that led to good performance. Reinf
Related categories
Chapter list
Reinforcement Learning00:06
Outline01:00
Reinforcement Learning (RL) in a Nutshell01:46
RL Can Solve Hard Problems04:10
Examples07:58
Partially Observable Markov Decision Processes08:47
Types of RL14:17
Optimality Criteria16:03
Criteria Continued17:45
Discounted or Average?19:10
Average versus Discounted21:15
Dynamic Programming23:05
Analytic Solution27:12
Value Iteration28:34
Value Iteration Continued29:49
Value Iteration Convergence32:32
Policy Iteration34:17
Policy Iteration, Pros and Cons36:35
Convergence Picture37:38
Our Progress...38:54