Login / Signup
Alternative Function Approximation Parameterizations for Solving Games: An Analysis of ƒ-Regression Counterfactual Regret Minimization.
Ryan D'Orazio
Dustin Morrill
James R. Wright
Michael Bowling
Published in:
AAMAS (2020)
Keyphrases
</>
function approximation
reinforcement learning
temporal difference learning algorithms
radial basis function
model free
regret minimization
temporal difference learning
training data
multi agent
dynamic programming
upper bound
temporal difference