Nikita JohnsonUREX: Under-appreciated Reward Exploration by Google BrainThe most widely-used exploration methods in reinforcement learning today (like entropy regularization and epsilon-greedy) have not changed…Jan 23, 2017Jan 23, 2017
Nikita JohnsonThe World’s First Cognition Platform to Power the Future of AI“The final missing piece in AI is Visual Cognition and Understanding. In order for this dream to be realized, it takes more than winning…Jan 12, 2017Jan 12, 2017