Dr. Mark Humphrys
School of Computing. Dublin City University.
Home
Blog
Research
Publications
Contact
Online coding site:
Ancient Brain
Search:
Teaching
Project ideas
CA170
CA318
CA686
Free open-source AI exercises
Reinforcement Learning - Reference
AI Links
Reinforcement Learning Links
Neural Networks Links
Kaelbling survey
DP
non-Markov worlds
RL course
Convergence of Q-learning
Sutton and Barto book
AI Lab
at umich.edu
RL wiki
(currently down)
Wikipedia
DP
MDP
Partially observable MDP
RL
Q-learning
Scholarpedia
RL
TD learning
Math
MathWorld
is good for quick definitions of things.
quadratic equations
e
Quadratic Equation Solver
Greek letters
Greek alphabet
(and
here
and
search
)
letter
name
HTML symbol
usage in RL
α
alpha
α
learning rate
γ
gamma
γ
discounting factor