Adaptive Symmetric Reward Noising for Reinforcement Learning

1 code implementation • 24 May 2019 • Refael Vivanti, Talya D. Sohlberg-Baris, Shlomo Cohen, Orna Cohen

We claim that some of the brittleness stems from variance differences, i. e. when different environment areas - states and/or actions - have different rewards variance.

Autonomous Driving Q-Learning +2