Adaptive Strategies and Regret Minimization in Arbitrarily Varying Markov Environments.

Shie Mannor Nahum Shimkin

Published in: COLT/EuroCOLT (2001)

Keyphrases

adaptive strategies
regret minimization
particle swarm optimizer
game theoretic
nash equilibrium
semi markov
markov processes
markov chain
computing environments
neural network
markov model
conditional independence
dynamic environments
domain knowledge
multi agent
reinforcement learning
real world