-
公开(公告)号：US11429892B2
公开(公告)日：2022-08-30
申请号：US15934531
申请日：2018-03-23
Applicant: ADOBE INC.
Inventor： Sorathan Chaturapruek , Georgios Theocharous , Kent Andrew Edmonds
Abstract: Systems and methods provide a recommendation system for recommending sequential content. The training of a reinforcement learning (RL) agent is bootstrapped from passive data. The RL agent of the sequential recommendations system is trained using the passive data over a number of epochs involving interactions between the sequential recommendation system and user devices. At each epoch, available active data from previous epochs is obtained, and transition probabilities are generated from the passive data and at least one parameter derived from the currently available active data. Recommended content is selected based on a current state and the generated transition probabilities, and the active data is updated from the current epoch based on the recommended content and a resulting new state. A clustering approach can also be employed when deriving parameters from active data to balance model expressiveness and data sparsity.
-
公开(公告)号：US20190295004A1
公开(公告)日：2019-09-26
申请号：US15934531
申请日：2018-03-23
Applicant: ADOBE INC.
Inventor： Sorathan Chaturapruek , Georgios Theocharous , Kent Andrew Edmonds
Abstract: Systems and methods provide a recommendation system for recommending sequential content. The training of a reinforcement learning (RL) agent is bootstrapped from passive data. The RL agent of the sequential recommendations system is trained using the passive data over a number of epochs involving interactions between the sequential recommendation system and user devices. At each epoch, available active data from previous epochs is obtained, and transition probabilities are generated from the passive data and at least one parameter derived from the currently available active data. Recommended content is selected based on a current state and the generated transition probabilities, and the active data is updated from the current epoch based on the recommended content and a resulting new state. A clustering approach can also be employed when deriving parameters from active data to balance model expressiveness and data sparsity.
-
公开(公告)号：US20190236410A1
公开(公告)日：2019-08-01
申请号：US15886263
申请日：2018-02-01
Applicant: ADOBE INC.
Inventor： Sorathan Chaturapruek , Georgios Theocharous
CPC classification number: G06K9/6256 , G06K9/6218 , G06N7/005 , G06N20/00
Abstract: Systems and methods provide for bootstrapping a sequential recommendation system from passive data. A learning agent of the sequential recommendations system is trained using the passive data over a number of epochs involving interactions between the sequential recommendation system and user devices. At each epoch, available active data from previous epochs is obtained, and transition probabilities are generated from the passive data and at least one parameter derived from the currently available active data. A recommended action is selected given a current state and the generated transition probabilities, and the active data is updated from the current epoch based on the recommended action and a resulting new state. A clustering approach can also be employed when deriving parameters from active data to balance model expressiveness and data sparsity.
-
-
Search Results
3
records
(took 0.013 seconds)
