Related papers: Local Policy Improvement for Recommender Systems
Reinforcement learning (RL) aims to find an optimal policy by interaction with an environment. Consequently, learning complex behavior requires a vast number of samples, which can be prohibitive in practice. Nevertheless, instead of…
Predictive models are often introduced to decision-making tasks under the rationale that they improve performance over an existing decision-making policy. However, it is challenging to compare predictive performance against an existing…
Reinforcement learning (RL) algorithms are often categorized as either on-policy or off-policy depending on whether they use data from a target policy of interest or from a different behavior policy. In this paper, we study a subtle…
Learning in a lifelong setting, where the dynamics continually evolve, is a hard challenge for current reinforcement learning algorithms. Yet this would be a much needed feature for practical applications. In this paper, we propose an…
In the last decade we have observed a mass increase of information, in particular information that is shared through smartphones. Consequently, the amount of information that is available does not allow the average user to be aware of all…
Many model-based reinforcement learning (RL) methods follow a similar template: fit a model to previously observed data, and then use data from that model for RL or planning. However, models that achieve better training performance (e.g.,…
Modeling user sequential behaviors has recently attracted increasing attention in the recommendation domain. Existing methods mostly assume coherent preference in the same sequence. However, user personalities are volatile and easily…
Aligning generative models with human preference via RLHF typically suffers from overoptimization, where an imperfectly learned reward model can misguide the generative model to output undesired responses. We investigate this problem in a…
Preference alignment in Large Language Models (LLMs) has significantly improved their ability to adhere to human instructions and intentions. However, existing direct alignment algorithms primarily focus on relative preferences and often…
We study offline recommender learning from explicit rating feedback in the presence of selection bias. A current promising solution for the bias is the inverse propensity score (IPS) estimation. However, the performance of existing…
Recommender systems are a vital tool that helps us to overcome the information overload problem. They are being used by most e-commerce web sites and attract the interest of a broad scientific community. A recommender system uses data on…
Many web systems rank and present a list of items to users, from recommender systems to search and advertising. An important problem in practice is to evaluate new ranking policies offline and optimize them before they are deployed. We…
Recommender systems are expected to be assistants that help human users find relevant information automatically without explicit queries. As recommender systems evolve, increasingly sophisticated learning techniques are applied and have…
Reinforcement learning (RL) with sparse and deceptive rewards is challenging because non-zero rewards are rarely obtained. Hence, the gradient calculated by the agent can be stochastic and without valid information. Recent studies that…
We propose a method for building an interpretable recommender system for personalizing online content and promotions. Historical data available for the system consists of customer features, provided content (promotions), and user responses.…
Policy optimization is an effective reinforcement learning approach to solve continuous control tasks. Recent achievements have shown that alternating online and offline optimization is a successful choice for efficient trajectory reuse.…
We consider the problem of imitation learning from a finite set of expert trajectories, without access to reinforcement signals. The classical approach of extracting the expert's reward function via inverse reinforcement learning, followed…
Algorithmic recommendations and decisions have become ubiquitous in today's society. Many of these data-driven policies, especially in the realm of public policy, are based on known, deterministic rules to ensure their transparency and…
Collaborative filtering based recommendation learns users' preferences from all users' historical behavior data, and has been popular to facilitate decision making. R Recently, the fairness issue of recommendation has become more and more…
Negative user preference is an important context that is not sufficiently utilized by many existing recommender systems. This context is especially useful in scenarios where the cost of negative items is high for the users. In this work, we…