- document
-
Igl, Maximilian (author), Farquhar, Gregory (author), Luketina, Jelena (author), Böhmer, J.W. (author), Whiteson, Shimon (author)Non-stationarity can arise in Reinforcement Learning (RL) even in stationary environments. For example, most RL algorithms collect new data throughout training, using a non-stationary behaviour policy. Due to the transience of this non-stationarity, it is often not explicitly addressed in deep RL and a single neural network is continually...conference paper 2021