Results 1 
5 of
5
The Principle of Maximum Causal Entropy for Estimating Interacting Processes
"... Abstract—The principle of maximum entropy provides a powerful framework for estimating joint, conditional, and marginal probability distributions. However, there are many important distributions with elements of interaction and feedback where its applicability has not been established. This work pre ..."
Abstract

Cited by 1 (0 self)
 Add to MetaCart
(Show Context)
Abstract—The principle of maximum entropy provides a powerful framework for estimating joint, conditional, and marginal probability distributions. However, there are many important distributions with elements of interaction and feedback where its applicability has not been established. This work presents the principle of maximum causal entropy—an approach based on directed information theory for estimating an unknown process based on its interactions with a known process. We demonstrate the breadth of the approach using two applications: a predictive solution for inverse optimal control in decision processes and computing equilibrium strategies in sequential games. Index Terms—Maximum entropy, statistical estimation, causal entropy, directed information, inverse optimal control, inverse reinforcement learning, correlated equilibrium. I.
Polynomialtime Computation of Exact Correlated Equilibrium in Compact Games Jiang and LeytonBrown CE Papadimitriou and Roughgarden’s algorithm Numerical Precision Issues Algorithm for Exact Correlated Equilibrium References Correlated Equilibrium
"... n players player p’s pure strategy sp ∈ Sp pure strategy profile s ∈ S =∏np=1 Sp utility for p under pure strategy profile s is integer ups a CE is a distribution x over S: a trusted intermediary draws a strategy profile s from this distribution announce to each player p (privately) her own componen ..."
Abstract
 Add to MetaCart
n players player p’s pure strategy sp ∈ Sp pure strategy profile s ∈ S =∏np=1 Sp utility for p under pure strategy profile s is integer ups a CE is a distribution x over S: a trusted intermediary draws a strategy profile s from this distribution announce to each player p (privately) her own component sp p will have no incentive to choose another strategy, assuming others follow suggestions
Jiang and LeytonBrownProblem Formulation Papadimitriou and Roughgarden’s Algorithm Algorithm for Exact Correlated Equilibrium References
, 2011
"... natural learning dynamics converge to CE ..."