1Cademy - Reward functions and performance metrics (Using deep reinforcement learning for personalizing review sessions on e-learning platforms with spaced repetition)

Learn Before

Experiments (Using deep reinforcement learning for personalizing review sessions on e-learning platforms with spaced repetition)

Concept

Reward functions and performance metrics (Using deep reinforcement learning for personalizing review sessions on e-learning platforms with spaced repetition)

For different purposes, different reward functions were used.

The Goal: Maximize likelihood of expected number of recalled items: $R (s, \cdot) = \sum_{i=1}^{n} P[Z_i=1 | s]$
The Goal: Maximize likelihood of recalling all items: $R(s, \cdot) = \sum_{i=1}^{n} \log P[Z_I = 1 | s]$

In the paper the authors have defined the reward function as the average of the sum of the correct answers at every time step: $R(s, \cdot) = \sum_i Z_i$ $Z_i \sim P_i(\cdot | s)$

The reward function for the LSTM: $R_{RNN} = \sum_{i=0}^{n}P_{RNN}(Z_{i}^{j} | o_{0:j-1})$ Here n denotes number of items, j current interaction step, P_{RNN} the probability that the user will answer correctly item i and $o_t = (Z_{i}^{j}, i)$

0

1

Updated 2020-10-29

Contributors are:

Nineli Lashkarashvili

🏆 1

Who are from:

San Diego State University

🏆 1

Learn Before

Related