Table 1.
Example user-item voting’s matrix.
Table 2.
Binary form of Table 1.
Fig 1.
Cantor-diagonal traversal of 6×6 grid.
Fig 2.
Flow diagram of proposed methodology.
Table 3.
Snapshot of Q-table at some time instance for Q-learning.
Fig 3.
Example scenario to illustrate how rating is predicted by proposed algorithm.
Table 4.
Grid positions of biclusters across three datasets for used biclustering algorithms.
Fig 4.
Agent learning of ML100K dataset across various parameters.
Fig 5.
Agent learning of ML latest-small dataset across various parameters.
Fig 6.
Agent learning of FilmTrust dataset across various parameters.
Fig 7.
Performance of various biclustering algorithms on ML-100K dataset with Q- learning.
Fig 8.
Performance of various biclustering algorithms on ML-100K dataset with SARSA.
Table 5.
Evaluation results obtained with Q-learning on ML-100K.
Table 6.
Evaluation results obtained with SARSA on ML-100K.
Fig 9.
Performance of various biclustering algorithms on ML-latest-small dataset with Q-learning.
Fig 10.
Performance of various biclustering algorithms on ML-latest-small dataset with SARSA.
Table 7.
Evaluation metrics with Q-learning on ML-latest-small.
Table 8.
Evaluation metrics with SARSA on ML-latest-small.
Fig 11.
Performance of various biclustering algorithms on FilmTrust dataset with Q-learning.
Fig 12.
Performance of various biclustering algorithms on FilmTrust dataset with SARSA.
Table 9.
Competitor methods results on ML-100K dataset.
Table 10.
Competitor methods results on FilmTrust dataset.
Table 11.
Competitor methods results on ML-latest-small dataset.