Markov Decision Processes

Data Skeptic

Formally, an MDP is defined as the tuple containing states, actions, the transition function, and the reward function. The rest of this post will define each of these components.

Next Episodes

Data Skeptic

Colossus: The Forbin Project @ Data Skeptic

📆 2018-01-22 01:00


Data Skeptic

Neuroscience Frontiers @ Data Skeptic

📆 2018-01-18 01:00


Data Skeptic

Neuroscience Frontiers @ Data Skeptic

📆 2018-01-18 01:00


Data Skeptic

Word Clouds Revisited @ Data Skeptic

📆 2018-01-15 01:00


Data Skeptic

Neuroimaging and Big Data @ Data Skeptic

📆 2018-01-12 01:00