EPISODE · Jan 26, 2018 · 20 MIN
[MINI] Markov Decision Processes
from Data Skeptic · host Kyle Polich and Linh Da Tran
Formally, an MDP is defined as the tuple containing states, actions, the transition function, and the reward function. This podcast examines each of these and presents them in the context of simple examples. Despite MDPs suffering from the curse of dimensionality, they're a useful formalism and a basic concept we will expand on in future episodes.
Embed this episode
Ready to play
[MINI] Markov Decision Processes
No transcript for this episode yet
Similar Episodes
No similar episodes found.