| 
|
Quote: the goal of temporal difference methods is to match the learner's current prediction for a pattern with the next prediction at the next time step
topics >
all references >
references t-z >
Group:
artificial intelligence
Topic:
artificial neuron nets
Quotation Skeleton
The basic idea of TD [Temporal Difference] methods [for reinforcement learning] is that the learning is based on the difference between … prediction for the current input pattern more closely … Google-1 Google-2
Copyright clearance needed for quotation.
Group: artificial intelligence (14 topics, 500 quotes)
Topic: artificial neuron nets (29 items)