New Authentication Rolling Out - We're upgrading our sign-in process to give you one account across all Anaconda products! Browser users will see a refreshed sign-in flow, while CLI users will experience no changes.
Implements Q-Learning, a model-free form of reinforcement learning, described in work by Strehl, Li, Wiewiora, Langford & Littman (2006) <doi:10.1145/1143844.1143955>.
