4. For the following reinforcement learning algorithms: (a) Q-learning with fixed and 80% exploitation. (b) Q-learning with fixed k = 1/k and 80% exploitation.

4. For the following reinforcement learning algorithms:

(a) Q-learning with fixed α and 80% exploitation.

(b) Q-learning with fixed αk = 1/k and 80% exploitation.

(c) Q-learning with αk = 1/k and 100% exploitation.

(d) SARSA learning with αk = 1/k and 80% exploitation.

(e) SARSA learning with αk = 1/k and 100% exploitation.

(f) Feature-based SARSA learning with soft-max action selection.

(g) A model-based reinforcement learner with 50% exploitation.

(a) Which of the reinforcement learning algorithms will find the optimal policy, given enough time?

(b) Which ones will actually follow the optimal policy?