Adaptations of Transformer models, such as BERT4Rec and SASRec, achieve state-of-the-art performance in the sequential recommendation task according to accuracy-based metrics, such as NDCG. These models treat items as tokens and then utilise a score-and-rank approach (Top-K strategy), where the model first computes item scores and then ranks them according to this score. While this approach works well for accuracy-based metrics, it is hard to use it for optimising more complex beyond-accuracy metrics such as diversity. Recently, the GPTRec model, which uses a different Next-K strategy, has been proposed as an alternative to the Top-K models. In contrast with traditional Top-K recommendations, Next-K generates recommendations item-by-item and, therefore, can account for complex item-to-item interdependencies important for the beyond-accuracy measures. However, the original GPTRec paper focused only on accuracy in experiments and needed to address how to optimise the model for complex beyond-accuracy metrics. Indeed, training GPTRec for beyond-accuracy goals is challenging because the interaction training data available for training recommender systems typically needs to be aligned with beyond-accuracy recommendation goals. To solve the misalignment problem, we train GPTRec using a 2-stage approach: in the first stage, we use a teacher-student approach to train GPTRec, mimicking the behaviour of traditional Top-K models; in the second stage, we use Reinforcement Learning to align the model for beyond-accuracy goals. In particular, we experiment with increasing recommendation diversity and reducing popularity bias. Our experiments on two datasets show that in 3 out of 4 cases, GPTRec's Next-K generation approach offers a better tradeoff between accuracy and secondary metrics than classic greedy re-ranking techniques.
Deep Reinforcement Learning (DRL) is considered a potential framework to improve many real-world autonomous systems; it has attracted the attention of multiple and diverse fields. Nevertheless, the successful deployment in the real world is a test most of DRL models still need to pass. In this work we focus on this issue by reviewing and evaluating the research efforts from both domain-agnostic and domain-specific communities. On one hand, we offer a comprehensive summary of DRL challenges and summarize the different proposals to mitigate them; this helps identifying five gaps of domain-agnost…
Russian Quantum Center（俄罗斯量子中心）；Moscow Institute of Physics and Technology（莫斯科物理技术学院）；University of Oxford（牛津大学）；P. N. Lebedev Physics Institute（列别杰夫物理研究所）
Limitations in acquiring training data restrict potential applications of deep reinforcement learning (RL) methods to the training of real-world robots. Here we train an RL agent to align a Mach-Zehnder interferometer, which is an essential part of many optical experiments, based on images of interference fringes acquired by a monocular camera. The agent is trained in a simulated environment, without any hand-coded features or a priori information about the physics, and subsequently transferred to a physical interferometer. Thanks to a set of domain randomizations simulating uncertainties in p…
ReMax: A Simple, Effective, and Efficient Reinforcement Learning Method for Aligning Large Language Models
School of Data Science, The Chinese University of Hong Kong, Shenzhen（香港中文大学（深圳）数据科学学院）；Shenzhen Research Institute of Big Data（深圳大数据研究院）；National Key Laboratory for Novel Software Technology, Nanjing University（南京大学计算机软件新技术国家重点实验室）；Pazhou Laboratory (Huangpu)（琶洲实验室（黄埔））；China Shenzhen International Center For Industrial and Applied Mathematics（中国深圳国际工业与应用数学中心）
Aligning Frozen LLMs by Reinforcement Learning: An Iterative Reweight-then-Optimize Approach
University of Minnesota（明尼苏达大学）；Texas A&M University（德克萨斯A&M大学）；University of California, Davis（加利福尼亚大学戴维斯分校）；Amazon（亚马逊）；The Chinese University of Hong Kong（香港中文大学）
Stabilizing MoE Reinforcement Learning by Aligning Training and Inference Routers
State Key Laboratory of Multimedia Information Processing, School of Computer Science, Peking University（多媒体信息处理国家重点实验室，计算机学院，北京大学）；LLM-Core Xiaomi（小米LLM-Core）
Offline reinforcement learning (RL) is challenged by the distributional shift between learning policies and datasets. To address this problem, existing works mainly focus on designing sophisticated algorithms to explicitly or implicitly constrain the learned policy to be close to the behavior policy. The constraint applies not only to well-performing actions but also to inferior ones, which limits the performance upper bound of the learned policy. Instead of aligning the densities of two distributions, aligning the supports gives a relaxed constraint while still being able to avoid out-of-dist…
Russian Quantum Center（俄罗斯量子中心）；Moscow Institute of Physics and Technology（莫斯科物理技术学院）；University of Oxford（牛津大学）
Reinforcement learning is finding its way to real-world problem application, transferring from simulated environments to physical setups. In this work, we implement vision-based alignment of an optical Mach-Zehnder interferometer with a confocal telescope in one arm, which controls the diameter and divergence of the corresponding beam. We use a continuous action space; exponential scaling enables us to handle actions within a range of over two orders of magnitude. Our agent trains only in a simulated environment with domain randomizations. In an experimental evaluation, the agent significantly…
Inferring reward functions from demonstrations and pairwise preferences are auspicious approaches for aligning Reinforcement Learning (RL) agents with human intentions. However, state-of-the art methods typically focus on learning a single reward model, thus rendering it difficult to trade off different reward functions from multiple experts. We propose Multi-Objective Reinforced Active Learning (MORAL), a novel method for combining diverse demonstrations of social norms into a Pareto-optimal policy. Through maintaining a distribution over scalarization weights, our approach is able to interac…
LinguaFluid: Language Guided Fluid Control via Semantic Rewards in Reinforcement Learning
College of Environmental and Resource Sciences, Zhejiang University, Hangzhou, China（浙江大学环境与资源学院）；School of Engineering, Westlake University, Hangzhou, China（西湖大学工程学院）
We show how to assess a language model's knowledge of basic concepts of morality. We introduce the ETHICS dataset, a new benchmark that spans concepts in justice, well-being, duties, virtues, and commonsense morality. Models predict widespread moral judgments about diverse text scenarios. This requires connecting physical and social world knowledge to value judgements, a capability that may enable us to steer chatbot outputs or eventually regularize open-ended reinforcement learning agents. With the ETHICS dataset, we find that current language models have a promising but incomplete ability to…
EduAlign: Aligning Educational LLMs for Helpfulness, Personalization, and Creativity
Shanghai Innavation Institute（上海创新研究院）；Shanghai Institute of AI for Education（上海人工智能教育研究院）；School of Computer Science and Technology（计算机科学与技术学院）；Department of Educational Information Technology（教育信息技术系）
Zhejiang University（浙江大学）；Westlake University（西湖大学）；UC Berkeley（加州大学伯克利分校）；Institute of Advanced Technology, Westlake Institute for Advanced Study（西湖高等研究院前沿技术研究所）
Unsupervised reinforcement learning aims to acquire skills without prior goal representations, where an agent automatically explores an open-ended environment to represent goals and learn the goal-conditioned policy. However, this procedure is often time-consuming, limiting the rollout in some potentially expensive target environments. The intuitive approach of training in another interaction-rich environment disrupts the reproducibility of trained skills in the target environment due to the dynamics shifts and thus inhibits direct transferring. Assuming free access to a source environment, we…
