On Generative Agents in Recommendation

Recommender systems are the cornerstone of today's information dissemination, yet a disconnect between offline metrics and online performance greatly hinders their development. Addressing this challenge, we envision a recommendation simulator, capitalizing on recent breakthroughs in human-level intelligence exhibited by Large Language Models (LLMs). We propose Agent4Rec, a novel movie recommendation simulator, leveraging LLM-empowered generative agents equipped with user profile, memory, and actions modules specifically tailored for the recommender system. In particular, these agents' profile modules are initialized using the MovieLens dataset, capturing users' unique tastes and social traits; memory modules log both factual and emotional memories and are integrated with an emotion-driven reflection mechanism; action modules support a wide variety of behaviors, spanning both taste-driven and emotion-driven actions. Each agent interacts with personalized movie recommendations in a page-by-page manner, relying on a pre-implemented collaborative filtering-based recommendation algorithm. We delve into both the capabilities and limitations of Agent4Rec, aiming to explore an essential research question: to what extent can LLM-empowered generative agents faithfully simulate the behavior of real, autonomous humans in recommender systems? Extensive and multi-faceted evaluations of Agent4Rec highlight both the alignment and deviation between agents and user-personalized preferences. Beyond mere performance comparison, we explore insightful experiments, such as emulating the filter bubble effect and discovering the underlying causal relationships in recommendation tasks. Our codes are available at https://github.com/LehengTHU/Agent4Rec.

Constrained Bayesian Optimization with Adaptive Active Learning of Unknown Constraints

Optimizing objectives under constraints, where both the objectives and constraints are black box functions, is a common scenario in real-world applications such as scientific experimental design, design of medical therapies, and industrial process optimization. One popular approach to handling these complex scenarios is Bayesian Optimization (BO). In terms of theoretical behavior, BO is relatively well understood in the unconstrained setting, where its principles have been well explored and validated. However, when it comes to constrained Bayesian optimization (CBO), the existing framework often relies on heuristics or approximations without the same level of theoretical guarantees. In this paper, we delve into the theoretical and practical aspects of constrained Bayesian optimization, where the objective and constraints can be independently evaluated and are subject to noise. By recognizing that both the objective and constraints can help identify high-confidence regions of interest (ROI), we propose an efficient CBO framework that intersects the ROIs identified from each aspect to determine the general ROI. The ROI, coupled with a novel acquisition function that adaptively balances the optimization of the objective and the identification of feasible regions, enables us to derive rigorous theoretical justifications for its performance. We showcase the efficiency and robustness of our proposed CBO framework through empirical evidence and discuss the fundamental challenge of deriving practical regret bounds for CBO algorithms.

Quantifying Agent Interaction in Multi-agent Reinforcement Learning for Cost-efficient Generalization

Generalization poses a significant challenge in Multi-agent Reinforcement Learning (MARL). The extent to which an agent is influenced by unseen co-players depends on the agent's policy and the specific scenario. A quantitative examination of this relationship sheds light on effectively training agents for diverse scenarios. In this study, we present the Level of Influence (LoI), a metric quantifying the interaction intensity among agents within a given scenario and environment. We observe that, generally, a more diverse set of co-play agents during training enhances the generalization performance of the ego agent; however, this improvement varies across distinct scenarios and environments. LoI proves effective in predicting these improvement disparities within specific scenarios. Furthermore, we introduce a LoI-guided resource allocation method tailored to train a set of policies for diverse scenarios under a constrained budget. Our results demonstrate that strategic resource allocation based on LoI can achieve higher performance than uniform allocation under the same computation budget.

Blending Imitation and Reinforcement Learning for Robust Policy Improvement

While reinforcement learning (RL) has shown promising performance, its sample complexity continues to be a substantial hurdle, restricting its broader application across a variety of domains. Imitation learning (IL) utilizes oracles to improve sample efficiency, yet it is often constrained by the quality of the oracles deployed. which actively interleaves between IL and RL based on an online estimate of their performance. RPI draws on the strengths of IL, using oracle queries to facilitate exploration, an aspect that is notably challenging in sparse-reward RL, particularly during the early stages of learning. As learning unfolds, RPI gradually transitions to RL, effectively treating the learned policy as an improved oracle. This algorithm is capable of learning from and improving upon a diverse set of black-box oracles. Integral to RPI are Robust Active Policy Selection (RAPS) and Robust Policy Gradient (RPG), both of which reason over whether to perform state-wise imitation from the oracles or learn from its own value function when the learner's performance surpasses that of the oracles in a specific state. Empirical evaluations and theoretical analysis validate that RPI excels in comparison to existing state-of-the-art methodologies, demonstrating superior performance across various benchmark domains.

Beyond Reverse KL: Generalizing Direct Preference Optimization with Diverse Divergence Constraints

The increasing capabilities of large language models (LLMs) raise opportunities for artificial general intelligence but concurrently amplify safety concerns, such as potential misuse of AI systems, necessitating effective AI alignment. Reinforcement Learning from Human Feedback (RLHF) has emerged as a promising pathway towards AI alignment but brings forth challenges due to its complexity and dependence on a separate reward model. Direct Preference Optimization (DPO) has been proposed as an alternative, and it remains equivalent to RLHF under the reverse KL regularization constraint. This paper presents $f$-DPO, a generalized approach to DPO by incorporating diverse divergence constraints. We show that under certain $f$-divergences, including Jensen-Shannon divergence, forward KL divergences and $\alpha$-divergences, the complex relationship between the reward and optimal policy can also be simplified by addressing the Karush-Kuhn-Tucker conditions. This eliminates the need for estimating the normalizing constant in the Bradley-Terry model and enables a tractable mapping between the reward function and the optimal policy. Our approach optimizes LLMs to align with human preferences in a more efficient and supervised manner under a broad set of divergence constraints. Empirically, adopting these divergences ensures a balance between alignment performance and generation diversity. Importantly, $f$-DPO outperforms PPO-based methods in divergence efficiency, and divergence constraints directly influence expected calibration error (ECE).

BitCoin: Bidirectional Tagging and Supervised Contrastive Learning based Joint Relational Triple Extraction Framework

Relation triple extraction (RTE) is an essential task in information extraction and knowledge graph construction. Despite recent advancements, existing methods still exhibit certain limitations. They just employ generalized pre-trained models and do not consider the specificity of RTE tasks. Moreover, existing tagging-based approaches typically decompose the RTE task into two subtasks, initially identifying subjects and subsequently identifying objects and relations. They solely focus on extracting relational triples from subject to object, neglecting that once the extraction of a subject fails, it fails in extracting all triples associated with that subject. To address these issues, we propose BitCoin, an innovative Bidirectional tagging and supervised Contrastive learning based joint relational triple extraction framework. Specifically, we design a supervised contrastive learning method that considers multiple positives per anchor rather than restricting it to just one positive. Furthermore, a penalty term is introduced to prevent excessive similarity between the subject and object. Our framework implements taggers in two directions, enabling triples extraction from subject to object and object to subject. Experimental results show that BitCoin achieves state-of-the-art results on the benchmark datasets and significantly improves the F1 score on Normal, SEO, EPO, and multiple relation extraction tasks.

Settling the Sample Complexity of Online Reinforcement Learning

A central issue lying at the heart of online reinforcement learning (RL) is data efficiency. While a number of recent works achieved asymptotically minimal regret in online RL, the optimality of these results is only guaranteed in a ``large-sample'' regime, imposing enormous burn-in cost in order for their algorithms to operate optimally. How to achieve minimax-optimal regret without incurring any burn-in cost has been an open problem in RL theory. We settle this problem for the context of finite-horizon inhomogeneous Markov decision processes. Specifically, we prove that a modified version of Monotonic Value Propagation (MVP), a model-based algorithm proposed by \cite{zhang2020reinforcement}, achieves a regret on the order of (modulo log factors) \begin{equation*} \min\big\{ \sqrt{SAH^3K}, \,HK \big\}, \end{equation*} where $S$ is the number of states, $A$ is the number of actions, $H$ is the planning horizon, and $K$ is the total number of episodes. This regret matches the minimax lower bound for the entire range of sample size $K\geq 1$, essentially eliminating any burn-in requirement. It also translates to a PAC sample complexity (i.e., the number of episodes needed to yield $\varepsilon$-accuracy) of $\frac{SAH^3}{\varepsilon^2}$ up to log factor, which is minimax-optimal for the full $\varepsilon$-range. Further, we extend our theory to unveil the influences of problem-dependent quantities like the optimal value/cost and certain variances. The key technical innovation lies in the development of a new regret decomposition strategy and a novel analysis paradigm to decouple complicated statistical dependency -- a long-standing challenge facing the analysis of online RL in the sample-hungry regime.

Learning Regions of Interest for Bayesian Optimization with Adaptive Level-Set Estimation

We study Bayesian optimization (BO) in high-dimensional and non-stationary scenarios. Existing algorithms for such scenarios typically require extensive hyperparameter tuning, which limits their practical effectiveness. We propose a framework, called BALLET, which adaptively filters for a high-confidence region of interest (ROI) as a superlevel-set of a nonparametric probabilistic model such as a Gaussian process (GP). Our approach is easy to tune, and is able to focus on local region of the optimization space that can be tackled by existing BO methods. The key idea is to use two probabilistic models: a coarse GP to identify the ROI, and a localized GP for optimization within the ROI. We show theoretically that BALLET can efficiently shrink the search space, and can exhibit a tighter regret bound than standard BO without ROI filtering. We demonstrate empirically the effectiveness of BALLET on both synthetic and real-world optimization tasks.

Active Policy Improvement from Multiple Black-box Oracles

Reinforcement learning (RL) has made significant strides in various complex domains. However, identifying an effective policy via RL often necessitates extensive exploration. Imitation learning aims to mitigate this issue by using expert demonstrations to guide exploration. In real-world scenarios, one often has access to multiple suboptimal black-box experts, rather than a single optimal oracle. These experts do not universally outperform each other across all states, presenting a challenge in actively deciding which oracle to use and in which state. We introduce MAPS and MAPS-SE, a class of policy improvement algorithms that perform imitation learning from multiple suboptimal oracles. In particular, MAPS actively selects which of the oracles to imitate and improve their value function estimates, and MAPS-SE additionally leverages an active state exploration criterion to determine which states one should explore. We provide a comprehensive theoretical analysis and demonstrate that MAPS and MAPS-SE enjoy sample efficiency advantage over the state-of-the-art policy improvement algorithms. Empirical results show that MAPS-SE significantly accelerates policy optimization via state-wise imitation learning from multiple oracles across a broad spectrum of control tasks in the DeepMind Control Suite. Our code is publicly available at: https://github.com/ripl/maps.

Towards Faster Non-Asymptotic Convergence for Diffusion-Based Generative Models

Diffusion models, which convert noise into new data instances by learning to reverse a Markov diffusion process, have become a cornerstone in contemporary generative modeling. While their practical power has now been widely recognized, the theoretical underpinnings remain far from mature. In this work, we develop a suite of non-asymptotic theory towards understanding the data generation process of diffusion models in discrete time, assuming access to reliable estimates of the (Stein) score functions. For a popular deterministic sampler (based on the probability flow ODE), we establish a convergence rate proportional to $1/T$ (with $T$ the total number of steps), improving upon past results; for another mainstream stochastic sampler (i.e., a type of the denoising diffusion probabilistic model (DDPM)), we derive a convergence rate proportional to $1/\sqrt{T}$, matching the state-of-the-art theory. Our theory imposes only minimal assumptions on the target data distribution (e.g., no smoothness assumption is imposed), and is developed based on an elementary yet versatile non-asymptotic approach without resorting to toolboxes for SDEs and ODEs. Further, we design two accelerated variants, improving the convergence to $1/T^2$ for the ODE-based sampler and $1/T$ for the DDPM-type sampler, which might be of independent theoretical and empirical interest.