issues
search
FrancisLeon
/
Reinforement-Learning-
0
stars
0
forks
source link
Design the MDP of the thesis
#5
Open
FrancisLeon
opened
7 years ago
FrancisLeon
commented
7 years ago
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).
MDP of Wayne:
goal: the performance of the learner
agent: the control system or app
action: easiness
environment:
state:
acq_reps_since_lapse
ret_reps_since_lapse
scheduled_interval
actual_interval
reward: the extent of change of the grade