~/talk

An Alternative Softmax Operator for Reinforcement Learning

links:none on file
slides:none on file

Introduces the Mellowmax (mellomax) operator: log of the average of e^{omega·Q}/omega (a softened Boltzmann-style average) and proves it satisfies a non-expansion contraction property so generalized value iteration has a unique fixed point and fast convergence. Experiments show Boltzmann sometimes fails (8 of 200 random MDPs nonterminating, 3 with multiple fixed points) while mellanax never does. Replacing max with mellomax in Deep Q-learning replaces max in DQN removes the target network and yields more stable learning and higher returns on several Atari-style games.

AI-written summary · about

  1. 0:00Introduction
  2. 5:05Pacman in a Grid
  3. 7:47NonExpansion Property
  4. 14:39Contraction Property
  5. 15:15Properties
  6. 16:13Algorithm
  7. 17:26Bellman Operator
  8. 18:54Boltzmann Operator
  9. 23:01Deep Q Learning
  10. 27:30Questions
~/search
type to search 6,249 conferences, 138,987 speakers and 185,172 talks
~/help
cmdctrl k
search every conference, speaker and series
/
focus the filter search
h
home
c
conferences
s
speakers
e
series
t
light / dark — the status bar button does the same
?
this help
esc
close this, then clear every filter — or just the search, while you are typing in it

Ignored while you are typing. Pages without a filter rail have no search to focus.