Rethinking Reinforcement Learning for Recommendation: A Prompt Perspective
June 15, 2022 ยท Declared Dead ยท ๐ Annual International ACM SIGIR Conference on Research and Development in Information Retrieval
"No code URL or promise found in abstract"
Evidence collected by the PWNC Scanner
Authors
Xin Xin, Tiago Pimentel, Alexandros Karatzoglou, Pengjie Ren, Konstantina Christakopoulou, Zhaochun Ren
arXiv ID
2206.07353
Category
cs.IR: Information Retrieval
Citations
43
Venue
Annual International ACM SIGIR Conference on Research and Development in Information Retrieval
Last Checked
3 months ago
Abstract
Modern recommender systems aim to improve user experience. As reinforcement learning (RL) naturally fits this objective -- maximizing an user's reward per session -- it has become an emerging topic in recommender systems. Developing RL-based recommendation methods, however, is not trivial due to the \emph{offline training challenge}. Specifically, the keystone of traditional RL is to train an agent with large amounts of online exploration making lots of `errors' in the process. In the recommendation setting, though, we cannot afford the price of making `errors' online. As a result, the agent needs to be trained through offline historical implicit feedback, collected under different recommendation policies; traditional RL algorithms may lead to sub-optimal policies under these offline training settings. Here we propose a new learning paradigm -- namely Prompt-Based Reinforcement Learning (PRL) -- for the offline training of RL-based recommendation agents. While traditional RL algorithms attempt to map state-action input pairs to their expected rewards (e.g., Q-values), PRL directly infers actions (i.e., recommended items) from state-reward inputs. In short, the agents are trained to predict a recommended item given the prior interactions and an observed reward value -- with simple supervised learning. At deployment time, this historical (training) data acts as a knowledge base, while the state-reward pairs are used as a prompt. The agents are thus used to answer the question: \emph{ Which item should be recommended given the prior interactions \& the prompted reward value}? We implement PRL with four notable recommendation models and conduct experiments on two real-world e-commerce datasets. Experimental results demonstrate the superior performance of our proposed methods.
Community Contributions
Found the code? Know the venue? Think something is wrong? Let us know!
๐ Similar Papers
In the same crypt โ Information Retrieval
R.I.P.
๐ป
Ghosted
R.I.P.
๐ป
Ghosted
LightGCN: Simplifying and Powering Graph Convolution Network for Recommendation
R.I.P.
๐ป
Ghosted
Graph Convolutional Neural Networks for Web-Scale Recommender Systems
๐
๐
Old Age
Neural Graph Collaborative Filtering
R.I.P.
๐ป
Ghosted
Self-Attentive Sequential Recommendation
R.I.P.
๐ป
Ghosted
DeepFM: A Factorization-Machine based Neural Network for CTR Prediction
Died the same way โ ๐ป Ghosted
R.I.P.
๐ป
Ghosted
Language Models are Few-Shot Learners
R.I.P.
๐ป
Ghosted
PyTorch: An Imperative Style, High-Performance Deep Learning Library
R.I.P.
๐ป
Ghosted
XGBoost: A Scalable Tree Boosting System
R.I.P.
๐ป
Ghosted