Most of the existing deep reinforcement learning (RL) approaches for session-based recommendations either rely on costly online interactions with real users, or rely on potentially biased rule-based or data-driven user-behavior models for learning. In this work, we instead focus on learning recommendation policies in the pure batch or offline setting, i.e. learning policies solely from offline historical interaction logs or batch data generated from an unknown and sub-optimal behavior policy, without further access to data from the real-world or user-behavior models. We propose BCD4Rec: Batch-Constrained Distributional RL for Session-based Recommendations. BCD4Rec builds upon the recent advances in batch (offline) RL and distributional RL to learn from offline logs while dealing with the intrinsically stochastic nature of rewards from the users due to varied latent interest preferences (environments). We demonstrate that BCD4Rec significantly improves upon the behavior policy as well as strong RL and non-RL baselines in the batch setting in terms of standard performance metrics like Click Through Rates or Buy Rates. Other useful properties of BCD4Rec include: i. recommending items from the correct latent categories indicating better value estimates despite large action space (of the order of number of items), and ii. overcoming popularity bias in clicked or bought items typically present in the offline logs.
University of Illinois at Urbana-Champaign（伊利诺伊大学厄巴纳-香槟分校）；Tsinghua University（清华大学）
Motivated by practical needs such as large-scale learning, we study the impact of adaptivity constraints to linear contextual bandits, a central problem in online active learning. We consider two popular limited adaptivity models in literature: batch learning and rare policy switches. We show that, when the context vectors are adversarially chosen in $d$-dimensional linear contextual bandits, the learner needs $O(d \log d \log T)$ policy switches to achieve the minimax-optimal regret, and this is optimal up to $\mathrm{poly}(\log d, \log \log T)$ factors; for stochastic context vectors, even i…
ISAE-SUPAERO（法国高等航空航天学院）；Université de Toulouse（图卢兹大学）；Google Research（谷歌研究院）
Several algorithms have been proposed to sample non-uniformly the replay buffer of deep Reinforcement Learning (RL) agents to speed-up learning, but very few theoretical foundations of these sampling schemes have been provided. Among others, Prioritized Experience Replay appears as a hyperparameter sensitive heuristic, even though it can provide good performance. In this work, we cast the replay buffer sampling problem as an importance sampling one for estimating the gradient. This allows deriving the theoretically optimal sampling distribution, yielding the best theoretical convergence speed.…
In many contemporary applications such as healthcare, finance, robotics, and recommendation systems, continuous deployment of new policies for data collection and online learning is either cost ineffective or impractical. We consider a setting that lies between pure offline reinforcement learning (RL) and pure online RL called deployment constrained RL in which the number of policy deployments for data sampling is limited. To solve this challenging task, we propose a new algorithmic learning framework called Model-based Uncertainty regularized and Sample Efficient Batch Optimization (MUSBO). O…
The distributional perspective on reinforcement learning (RL) has given rise to a series of successful Q-learning algorithms, resulting in state-of-the-art performance in arcade game environments. However, it has not yet been analyzed how these findings from a discrete setting translate to complex practical applications characterized by noisy, high dimensional and continuous state-action spaces. In this work, we propose Quantile QT-Opt (Q2-Opt), a distributional variant of the recently introduced distributed Q-learning algorithm for continuous domains, and examine its behaviour in a series of …
Quantile-Coupled Flow Matching for Distributional Reinforcement Learning
Oxford Robotics Institute, University of Oxford（牛津大学机器人研究所）；Bristol Robotics Laboratory, University of the West of England（布里斯托尔机器人实验室，西英格兰大学）；Dyson Institute of Engineering & Technology（戴森工程与技术研究院）
The University of Manchester（曼彻斯特大学）；Imperial College London（伦敦帝国理工学院）
Reinforcement Learning (RL) has recently received significant attention from the process systems engineering and control communities. Recent works have investigated the application of RL to identify optimal scheduling decision in the presence of uncertainty. In this work, we present a RL methodology tailored to efficiently address production scheduling problems in the presence of uncertainty. We consider commonly imposed restrictions on these problems such as precedence and disjunctive constraints which are not naturally considered by RL in other contexts. Additionally, this work naturally ena…
Recent years have seen a significant amount of interests in Sequential Recommendation (SR), which aims to understand and model the sequential user behaviors and the interactions between users and items over time. Surprisingly, despite the huge success Sequential Recommendation has achieved, there is little study on Sequential Search (SS), a twin learning task that takes into account a user's current and past search queries, in addition to behavior on historical query sessions. The SS learning task is even more important than the counterpart SR task for most of E-commence companies due to its m…
In this paper, we propose a novel domain adaptation method for the source-free setting. In this setting, we cannot access source data during adaptation, while unlabeled target data and a model pretrained with source data are given. Due to lack of source data, we cannot directly match the data distributions between domains unlike typical domain adaptation algorithms. To cope with this problem, we propose utilizing batch normalization statistics stored in the pretrained model to approximate the distribution of unobserved source data. Specifically, we fix the classifier part of the model during a…
Mode-Dependent Rectification for Stable PPO Training
I3S, Inria, Université Côte d'Azur, Nice, France（I3S、Inria、法国蔚蓝海岸大学）；Department of Control and Computer Engineering, Politecnico di Torino, Turin, Italy（控制与计算机工程系、托里尼理工学院）
ANITI - Artificial and Natural Intelligence Toulouse Institute（图卢兹人工智能与自然智能研究所）；Université de Toulouse（图卢兹大学）；ISAE-SUPAERO（法国国立高等航空航天学院）
The training of autonomous agents often requires expensive and unsafe trial-and-error interactions with the environment. Nowadays several data sets containing recorded experiences of intelligent agents performing various tasks, spanning from the control of unmanned vehicles to human-robot interaction and medical applications are accessible on the internet. With the intention of limiting the costs of the learning procedure it is convenient to exploit the information that is already available rather than collecting new data. Nevertheless, the incapability to augment the batch can lead the autono…
The Chinese University of Hong Kong, Shenzhen（香港中文大学（深圳））；The University of Texas at Austin（德克萨斯大学奥斯汀分校）；Shenzhen Institute of Artificial Intelligence and Robotics for Society（深圳市人工智能与机器人研究院）
In a sequential decision-making problem, off-policy evaluation estimates the expected cumulative reward of a target policy using logged trajectory data generated from a different behavior policy, without execution of the target policy. Reinforcement learning in high-stake environments, such as healthcare and education, is often limited to off-policy settings due to safety or ethical concerns, or inability of exploration. Hence it is imperative to quantify the uncertainty of the off-policy estimate before deployment of the target policy. In this paper, we propose a novel framework that provides…
Offline reinforcement learning (RL) refers to the problem of learning policies entirely from a large batch of previously collected data. This problem setting offers the promise of utilizing such datasets to acquire policies without any costly or dangerous active exploration. However, it is also challenging, due to the distributional shift between the offline training data and those states visited by the learned policy. Despite significant recent progress, the most successful prior methods are model-free and constrain the policy to the support of data, precluding generalization to unseen states…
This paper presents the D2KLab team's approach to the RecSys Challenge 2019 which focuses on the task of recommending accommodations based on user sessions. What is the feeling of a person who says "Rooms of the hotel are enormous, staff are friendly and efficient"? It is positive. Similarly to the sequence of words in a sentence where one can affirm what the feeling is, analysing a sequence of actions performed by a user in a website can lead to predict what will be the item the user will add to his basket at the end of the shopping session. We propose to use a many-to-one recurrent neural ne…
RIKEN Center for Advanced Intelligence Project (RIKEN AIP)（理化学研究所先进智能项目中心）；Advanced Telecommunications Research Institute International (ATR)（国际电气通信基础技术研究所）
Electroencephalography (EEG) provides access to neuronal dynamics non-invasively with millisecond resolution, rendering it a viable method in neuroscience and healthcare. However, its utility is limited as current EEG technology does not generalize well across domains (i.e., sessions and subjects) without expensive supervised re-calibration. Contemporary methods cast this transfer learning (TL) problem as a multi-source/-target unsupervised domain adaptation (UDA) problem and address it with deep learning or shallow, Riemannian geometry aware alignment methods. Both directions have, so far, fa…
The recent emergence of reinforcement learning has created a demand for robust statistical inference methods for the parameter estimates computed using these algorithms. Existing methods for statistical inference in online learning are restricted to settings involving independently sampled observations, while existing statistical inference methods in reinforcement learning (RL) are limited to the batch setting. The online bootstrap is a flexible and efficient approach for statistical inference in linear stochastic approximation algorithms, but its efficacy in settings involving Markov noise, s…
Mathematics Institute, University of Warwick（沃里克大学数学研究所）；Warwick Manufacturing Group, University of Warwick（沃里克大学制造集团）；Department of Statistics, University of Warwick（沃里克大学统计系）；Alan Turing Institute, London, UK（艾伦·图灵研究所）
Stanford University（斯坦福大学）；Georgia Institute of Technology（佐治亚理工学院）；Pinterest
Recommender systems that can learn from cross-session data to dynamically predict the next item a user will choose are crucial for online platforms. However, existing approaches often use out-of-the-box sequence models which are limited by speed and memory consumption, are often infeasible for production environments, and usually do not incorporate cross-session information, which is crucial for effective recommendations. Here we propose Hierarchical Temporal Convolutional Networks (HierTCN), a hierarchical deep learning architecture that makes dynamic recommendations based on users' sequentia…
Distributional Training Data Attribution: What do Influence Functions Sample?
University of Cambridge（剑桥大学）；Max Planck Institute for Intelligent Systems（马克斯·普朗克智能系统研究所）；University of Bristol（布里斯托大学）；Mila - Quebec AI Institute（米拉-魁北克人工智能研究所）；University of Toronto（多伦多大学）；Vector Institute（向量研究所）；Alan Turing Institute（艾伦·图灵研究所）
University of Texas at Austin（德克萨斯大学奥斯汀分校）；Michigan State University（密歇根州立大学）
Federated learning (FL) emerges as a popular distributed learning schema that learns a model from a set of participating users without sharing raw data. One major challenge of FL comes with heterogeneous users, who may have distributionally different (or non-iid) data and varying computation resources. As federated users would use the model for prediction, they often demand the trained model to be robust against malicious attackers at test time. Whereas adversarial training (AT) provides a sound solution for centralized learning, extending its usage for federated users has imposed significant …
