Tagged Questions
4
votes
0answers
106 views
'Model-free' learning in humans
In reinforcement learning, there is a stark distinction between model-based and model-free learning algorithms, where model-free methods don't make use any explicit information about the dynamics of ...
5
votes
1answer
81 views
Need good example of two domains involving different procedural knowledge yet sharing same high-level strategies
Working in the domain of intelligent tutoring systems, I have to prove (or disprove) that explicit teaching of high-level strategies will allow students to use learned strategies across different ...
9
votes
1answer
187 views
Are there any connectionist models that integrate reinforcement and fully supervised learning?
I've been working on modeling some phenomena involving real-time control in an environment with inherent rewards (specifically, playing a 'pong'-like game), and it's increasingly looking like ...
