AI & MLRecommendedAIML-RL-011
Markov Decision Processes
States, actions, transitions, rewards, and discount: the formal problem RL solves.
- Difficulty
- 3 / 5
- Importance
- 4 / 5
- Study time
- 1–2 h
- Kind of work
- Mixed
Why it matters
The learner can specify a small gridworld as an MDP and explain how the discount factor changes which policy is best.