Nodoka Shibuya, Yoshiki Miyazaki, Kentarou Kurashige. Suggestion of probabilistic reward-independent knowledge for dynamic environment in reinforcement learning. In International Symposium on Micro-NanoMechatronics and Human Science, MHS 2011, Nagoya, Japan, November 6-9, 2011. pages 140-145, IEEE, 2011. [doi]
Abstract is missing.