Two-Stage Constrained Actor-Critic for Short Video Recommendation

by   Qingpeng Cai, et al.

The wide popularity of short videos on social media poses new opportunities and challenges to optimize recommender systems on the video-sharing platforms. Users sequentially interact with the system and provide complex and multi-faceted responses, including watch time and various types of interactions with multiple videos. One the one hand, the platforms aims at optimizing the users' cumulative watch time (main goal) in long term, which can be effectively optimized by Reinforcement Learning. On the other hand, the platforms also needs to satisfy the constraint of accommodating the responses of multiple user interactions (auxiliary goals) such like, follow, share etc. In this paper, we formulate the problem of short video recommendation as a Constrained Markov Decision Process (CMDP). We find that traditional constrained reinforcement learning algorithms can not work well in this setting. We propose a novel two-stage constrained actor-critic method: At stage one, we learn individual policies to optimize each auxiliary signal. At stage two, we learn a policy to (i) optimize the main signal and (ii) stay close to policies learned at the first stage, which effectively guarantees the performance of this main policy on the auxiliaries. Through extensive offline evaluations, we demonstrate effectiveness of our method over alternatives in both optimizing the main goal as well as balancing the others. We further show the advantage of our method in live experiments of short video recommendations, where it significantly outperforms other baselines in terms of both watch time and interactions. Our approach has been fully launched in the production system to optimize user experiences on the platform.


Constrained Reinforcement Learning for Short Video Recommendation

The wide popularity of short videos on social media poses new opportunit...

Reinforcing User Retention in a Billion Scale Short Video Recommender System

Recently, short video platforms have achieved rapid user growth by recom...

Reinforcement Learning to Optimize Lifetime Value in Cold-Start Recommendation

Recommender system plays a crucial role in modern E-commerce platform. D...

Reinforcement Learning Under Algorithmic Triage

Methods to learn under algorithmic triage have predominantly focused on ...

Synthesizing Programmatic Policies with Actor-Critic Algorithms and ReLU Networks

Programmatically Interpretable Reinforcement Learning (PIRL) encodes pol...

Exploiting Cognitive Structure for Adaptive Learning

Adaptive learning, also known as adaptive teaching, relies on learning p...

Supervised Reinforcement Learning with Recurrent Neural Network for Dynamic Treatment Recommendation

Dynamic treatment recommendation systems based on large-scale electronic...

Please sign up or login with your details

Forgot password? Click here to reset