Dr. Mark Humphrys

School of Computing. Dublin City University.

Home      Blog      Teaching      Research      Contact

Search:

CA216      CA249      CA318

CA400      CA651      CA668


Page moved (or not found)

Searching for new location of page ..

Building up a running average
Notes/RL/average.html

The Control Policy
Notes/RL/control.policy.html

Convergence
Notes/RL/convergence.html

Exercise - long-term reward
Notes/RL/exercise.html

How Q-learning works
Notes/RL/how.q.html

Learning from Rewards (Reinforcement Learning, RL) as Pattern Classification
Notes/RL/intro.html

Building a model of Pxa(r)
Notes/RL/model.r.html

Building a model of Pxa(y)
Notes/RL/model.y.html

Neural Networks in RL
Notes/RL/neural.html

Q-learning
Notes/RL/q.html

Q-learning with a Neural Network
Notes/RL/q.neural.html

Reinforcement Learning - Reference
Notes/RL/ref.html

RL - The task
Notes/RL/rl.task.html

RL - The world
Notes/RL/rl.world.html

State-space control
Notes/RL/statespace.html

Coding the state-space as a lookup-table
Notes/RL/statespace.lookup.html

Learning rate that does not start at 1
Notes/RL/t.html

Sample implementation - the HouseRobot problem
Notes/RL/Code/code.houserobot.html

Sample code - How to implement vectors and the state-space as a lookup table
Notes/RL/Code/code.lookup.html

Sample code - How to implement Q-learning
Notes/RL/Code/code.q.html

Sample code for Q-learning
Notes/RL/Code/



Or try searching for what you are looking for:

Search my professional site:

Search my History and Genealogy site: