Exploiting Structure in Offline Multi-Agent RL: The Benefits of Low Interaction Rank

We study the problem of learning an approximate equilibrium in the offline multi-agent reinforcement learning (MARL) setting. We introduce a structural assumption -- the interaction rank -- and establish that functions with low interaction rank are significantly more robust to distribution shift compared to general ones. Leveraging this observation, we demonstrate that utilizing function classes with low interaction rank, when combined with regularization and no-regret learning, admits decentralized, computationally and statistically efficient learning in offline MARL. Our theoretical results are complemented by experiments that showcase the potential of critic architectures with low interaction rank in offline MARL, contrasting with commonly used single-agent value decomposition architectures.

Uncertainty of Joint Neural Contextual Bandit

Contextual bandit learning is increasingly favored in modern large-scale recommendation systems. To better utlize the contextual information and available user or item features, the integration of neural networks have been introduced to enhance contextual bandit learning and has triggered significant interest from both academia and industry. However, a major challenge arises when implementing a disjoint neural contextual bandit solution in large-scale recommendation systems, where each item or user may correspond to a separate bandit arm. The huge number of items to recommend poses a significant hurdle for real world production deployment. This paper focuses on a joint neural contextual bandit solution which serves all recommending items in one single model. The output consists of a predicted reward $\mu$, an uncertainty $\sigma$ and a hyper-parameter $\alpha$ which balances exploitation and exploration, e.g., $\mu + \alpha \sigma$. The tuning of the parameter $\alpha$ is typically heuristic and complex in practice due to its stochastic nature. To address this challenge, we provide both theoretical analysis and experimental findings regarding the uncertainty $\sigma$ of the joint neural contextual bandit model. Our analysis reveals that $\alpha$ demonstrates an approximate square root relationship with the size of the last hidden layer $F$ and inverse square root relationship with the amount of training data $N$, i.e., $\sigma \propto \sqrt{\frac{F}{N}}$. The experiments, conducted with real industrial data, align with the theoretical analysis, help understanding model behaviors and assist the hyper-parameter tuning during both offline training and online deployment.

Pearl: A Production-ready Reinforcement Learning Agent

Reinforcement Learning (RL) offers a versatile framework for achieving long-term goals. Its generality allows us to formalize a wide range of problems that real-world intelligent systems encounter, such as dealing with delayed rewards, handling partial observability, addressing the exploration and exploitation dilemma, utilizing offline data to improve online performance, and ensuring safety constraints are met. Despite considerable progress made by the RL research community in addressing these issues, existing open-source RL libraries tend to focus on a narrow portion of the RL solution pipeline, leaving other aspects largely unattended. This paper introduces Pearl, a Production-ready RL agent software package explicitly designed to embrace these challenges in a modular fashion. In addition to presenting preliminary benchmark results, this paper highlights Pearl's industry adoptions to demonstrate its readiness for production usage. Pearl is open sourced on Github at github.com/facebookresearch/pearl and its official website is located at pearlagent.github.io.

Non-Stationary Contextual Bandit Learning via Neural Predictive Ensemble Sampling

Real-world applications of contextual bandits often exhibit non-stationarity due to seasonality, serendipity, and evolving social trends. While a number of non-stationary contextual bandit learning algorithms have been proposed in the literature, they excessively explore due to a lack of prioritization for information of enduring value, or are designed in ways that do not scale in modern applications with high-dimensional user-specific features and large action set, or both. In this paper, we introduce a novel non-stationary contextual bandit algorithm that addresses these concerns. It combines a scalable, deep-neural-network-based architecture with a carefully designed exploration mechanism that strategically prioritizes collecting information with the most lasting value in a non-stationary environment. Through empirical evaluations on two real-world recommendation datasets, which exhibit pronounced non-stationarity, we demonstrate that our approach significantly outperforms the state-of-the-art baselines.

Offline Reinforcement Learning for Optimizing Production Bidding Policies

The online advertising market, with its thousands of auctions run per second, presents a daunting challenge for advertisers who wish to optimize their spend under a budget constraint. Thus, advertising platforms typically provide automated agents to their customers, which act on their behalf to bid for impression opportunities in real time at scale. Because these proxy agents are owned by the platform but use advertiser funds to operate, there is a strong practical need to balance reliability and explainability of the agent with optimizing power. We propose a generalizable approach to optimizing bidding policies in production environments by learning from real data using offline reinforcement learning. This approach can be used to optimize any differentiable base policy (practically, a heuristic policy based on principles which the advertiser can easily understand), and only requires data generated by the base policy itself. We use a hybrid agent architecture that combines arbitrary base policies with deep neural networks, where only the optimized base policy parameters are eventually deployed, and the neural network part is discarded after training. We demonstrate that such an architecture achieves statistically significant performance gains in both simulated and at-scale production bidding environments. Our approach does not incur additional infrastructure, safety, or explainability costs, as it directly optimizes parameters of existing production routines without replacing them with black box-style models like neural networks.

Scalable Neural Contextual Bandit for Recommender Systems

High-quality recommender systems ought to deliver both innovative and relevant content through effective and exploratory interactions with users. Yet, supervised learning-based neural networks, which form the backbone of many existing recommender systems, only leverage recognized user interests, falling short when it comes to efficiently uncovering unknown user preferences. While there has been some progress with neural contextual bandit algorithms towards enabling online exploration through neural networks, their onerous computational demands hinder widespread adoption in real-world recommender systems. In this work, we propose a scalable sample-efficient neural contextual bandit algorithm for recommender systems. To do this, we design an epistemic neural network architecture, Epistemic Neural Recommendation (ENR), that enables Thompson sampling at a large scale. In two distinct large-scale experiments with real-world tasks, ENR significantly boosts click-through rates and user ratings by at least 9% and 6% respectively compared to state-of-the-art neural contextual bandit algorithms. Furthermore, it achieves equivalent performance with at least 29% fewer user interactions compared to the best-performing baseline algorithm. Remarkably, while accomplishing these improvements, ENR demands orders of magnitude fewer computational resources than neural contextual bandit baseline algorithms.

IQL-TD-MPC: Implicit Q-Learning for Hierarchical Model Predictive Control

Model-based reinforcement learning (RL) has shown great promise due to its sample efficiency, but still struggles with long-horizon sparse-reward tasks, especially in offline settings where the agent learns from a fixed dataset. We hypothesize that model-based RL agents struggle in these environments due to a lack of long-term planning capabilities, and that planning in a temporally abstract model of the environment can alleviate this issue. In this paper, we make two key contributions: 1) we introduce an offline model-based RL algorithm, IQL-TD-MPC, that extends the state-of-the-art Temporal Difference Learning for Model Predictive Control (TD-MPC) with Implicit Q-Learning (IQL); 2) we propose to use IQL-TD-MPC as a Manager in a hierarchical setting with any off-the-shelf offline RL algorithm as a Worker. More specifically, we pre-train a temporally abstract IQL-TD-MPC Manager to predict "intent embeddings", which roughly correspond to subgoals, via planning. We empirically show that augmenting state representations with intent embeddings generated by an IQL-TD-MPC manager significantly improves off-the-shelf offline RL agents' performance on some of the most challenging D4RL benchmark tasks. For instance, the offline RL algorithms AWAC, TD3-BC, DT, and CQL all get zero or near-zero normalized evaluation scores on the medium and large antmaze tasks, while our modification gives an average score over 40.

Optimizing Long-term Value for Auction-Based Recommender Systems via On-Policy Reinforcement Learning

Auction-based recommender systems are prevalent in online advertising platforms, but they are typically optimized to allocate recommendation slots based on immediate expected return metrics, neglecting the downstream effects of recommendations on user behavior. In this study, we employ reinforcement learning to optimize for long-term return metrics in an auction-based recommender system. Utilizing temporal difference learning, a fundamental reinforcement learning algorithm, we implement an one-step policy improvement approach that biases the system towards recommendations with higher long-term user engagement metrics. This optimizes value over long horizons while maintaining compatibility with the auction framework. Our approach is grounded in dynamic programming ideas which show that our method provably improves upon the existing auction-based base policy. Through an online A/B test conducted on an auction-based recommender system which handles billions of impressions and users daily, we empirically establish that our proposed method outperforms the current production system in terms of long-term user engagement metrics.

Optimism Based Exploration in Large-Scale Recommender Systems

Bandit learning algorithms have been an increasingly popular design choice for recommender systems. Despite the strong interest in bandit learning from the community, there remains multiple bottlenecks that prevent many bandit learning approaches from productionalization. Two of the most important bottlenecks are scaling to multi-task and A/B testing. Classic bandit algorithms, especially those leveraging contextual information, often requires reward for uncertainty estimation, which hinders their adoptions in multi-task recommender systems. Moreover, different from supervised learning algorithms, bandit learning algorithms emphasize greatly on the data collection process through their explorative nature. Such explorative behavior induces unfair evaluation for bandit learning agents in a classic A/B test setting. In this work, we present a novel design of production bandit learning life-cycle for recommender systems, along with a novel set of metrics to measure their efficiency in user exploration. We show through large-scale production recommender system experiments and in-depth analysis that our bandit agent design improves personalization for the production recommender system and our experiment design fairly evaluates the performance of bandit learning algorithms.

Deep Exploration for Recommendation Systems

We investigate the design of recommendation systems that can efficiently learn from sparse and delayed feedback. Deep Exploration can play an important role in such contexts, enabling a recommendation system to much more quickly assess a user's needs and personalize service. We design an algorithm based on Thompson Sampling that carries out Deep Exploration. We demonstrate through simulations that the algorithm can substantially amplify the rate of positive feedback relative to common recommendation system designs in a scalable fashion. These results demonstrate promise that we hope will inspire engineering of production recommendation systems that leverage Deep Exploration.