Abstract:
Recommender systems provide relevant products, information, and services to users. Deep reinforcement learning has been successfully applied to recommender systems, but data sparsity and cold-start still plague real-world tasks. We propose using users’ pervasive social networks to estimate action-values (Q) to address such issues. We develop a Social Attentive Deep Q-network (SADQN) to approximate the optimal action-value function based on the preferences of both individual users and social neighbors by successfully modeling their influence using a social attention layer. We propose SADQN++ to model the complex and diverse trade-offs between personal preferences and social influence for all involved users, making the agent more powerful and flexible in learning the optimal policies. SADQNs outperform deep reinforcement learning agents on real-world datasets with reasonable computation cost.
Note: Please discuss with our team before submitting this abstract to the college. This Abstract or Synopsis varies based on student project requirements.
Did you like this final year project?
To download this project Code with thesis report and project training... Click Here
