Firstly, let's recall what's the MDP:
A reinforcement learning task that satisfies the Markov property is called a Markov decision process, or MDP. If the state and action spaces are finite, then it is called a finite Markov decision process (finite MDP).
In Wayne's thesis:
Goal: performance of the learner
Agent: the control system or the app
Action: easiness: E = f(E', q)
Reward: the extent of change of grade
State: lapse: forget:
acq_reps_since_lapse: repetion times of acquisition since lapse
Firstly, let's recall what's the MDP: A reinforcement learning task that satisfies the Markov property is called a Markov decision process, or MDP. If the state and action spaces are finite, then it is called a finite Markov decision process (finite MDP).