The study of what actions an agent should take in a stochastic environment in order to maximize a cumulative reward.

learn more… | top users | synonyms

7
votes
0answers
495 views

How does goal-tracking and sign-tracking behaviour vary across species?

In Pavlonian (Classical) Conditioning, conditioned responses of an animal may vary. Some animals focus on the unconditioned stimulus (ie. food / location of food) while others may focus on the ...
6
votes
0answers
179 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 ...
6
votes
0answers
237 views

Refinements of Rescorla-Wagner model of classical conditioning

The Rescorla-Wagner model is one of the most commonly discussed mathematical models of classical conditioning. It was wildly popular when it came out in 1972, and very successful. The same math, is ...
3
votes
0answers
21 views

Frequency estimation in binary prediction task

In a binary prediction task, people often match choice probabilities to outcome probabilities (a phenomenon known as probability matching). However, under certain circumstances (eg, existence of a ...
1
vote
0answers
16 views

Structure for General Intelligence

I've just read Dan Rasmussen's paper on general intelligence and I was wondering what other approaches for complex, scalable and adaptable learning have been tried in the past? This question's scope ...
0
votes
0answers
23 views

A basic question on reinforcement learning

Reinforcement learning is defined not by characterizing learning methods, but by characterizing a learning problem. Any method that is well suited to solving that problem, we consider to be a ...