ancilcrayton / nonstationary-k-arm-bandits Goto Github PK
View Code? Open in Web Editor NEWThis project forked from iyaja/nonstationary-k-arm-bandits
Python code for a basic RL solution for the Non-stationary (action value function changes with time) k-arm bandit problem. Based on the book "Reinforcement learning: An introduction" by S.Sutton and Andrew G. Barto