MDPs & Value Functions

States, actions, rewards, the Bellman equations, and value vs Q functions.

0 / 4 solved

Question Tags Difficulty Success

1. The Dice Roller

mdptransitions

Easy —

2. Five Now Or Twenty Later

reinforcement-learningmdp +2

Medium —

3. Expected Reward Under A Stochastic Policy

reinforcement-learningmdp +2

Medium —

4. Averaging Q Into V

reinforcement-learningbellman +2

Medium 40%

Learning Resources

Sutton & Barto, Reinforcement Learning (free book)

David Silver, RL Course

Up next

4 of 4 questions here are still unsolved.

Next module Dynamic Programming