用Transformer做强化学习，解决冷启动用户推荐难题。
RLT4Rec: Reinforcement Learning Transformer for User Cold Start and Item Recommendation
- 基于用户历史(物品,评分)序列，直接预测下个推荐物品。
- 无需状态观测，自动平衡新用户探索与老用户利用。
- 训练稳定快速，即使在差数据上也能生成高评分推荐序列。
我们提出一种新的序列化Transformer强化学习架构RLT4Rec，证明其在多种物品推荐任务中表现优异。RLT4Rec采用较简单的Transformer结构，输入用户的(物品,评分)历史，输出应推荐给用户的下一个物品。与现有强化学习方法不同，无需输入状态观测或进行估计。RLT4Rec在同一框架内处理新用户和成熟用户，并能自动平衡新用户所需的“探索”与成熟用户更合适的“利用”。RLT4Rec的训练过程稳健且迅速，对训练数据的选择不敏感，即使在低质量数据上训练，也能学习生成用户倾向于高评分的个性化推荐序列。
原文摘要 · Abstract (English)
We introduce a new sequential transformer reinforcement learning architecture RLT4Rec and demonstrate that it achieves excellent performance in a range of item recommendation tasks. RLT4Rec uses a relatively simple transformer architecture that takes as input the user's (item,rating) history and outputs the next item to present to the user. Unlike existing RL approaches, there is no need to input a state observation or estimate. RLT4Rec handles new users and established users within the same consistent framework and automatically balances the "exploration" needed to discover the preferences of a new user with the "exploitation" that is more appropriate for established users. Training of RLT4Rec is robust and fast and is insensitive to the choice of training data, learning to generate "good" personalised sequences that the user tends to rate highly even when trained on "bad" data.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。