Markov-Chain-Based Agents for k-Armed Bandit Problem.

Vladyslav Sarnatskyi Igor Baklan

Published in: ISDMCI (2021)

Keyphrases

markov chain
steady state
multi agent systems
multi agent
finite state
monte carlo
stationary distribution
markov model
transition probabilities
monte carlo method
monte carlo simulation
random walk
markov process
state space
multiple agents
transition matrix
stochastic process
search algorithm
support vector