PyTorchKR Papers

최신 논문

총 641편
태그·기간 등 상세 필터

카테고리 탐색

로그인 후 이 태그 구독

arXiv:2309.09832

Task Selection and Assignment for Multi-modal Multi-task Dialogue Act Classification with Non-stationary Multi-armed Bandits

Multi-task learning (MTL) aims to improve the performance of a primary task by jointly learning with related auxiliary tasks. Traditional MTL methods select tasks randomly during training. However, both previous studies and our results suggest that such a random selection of tasks may not be helpful, and can even be harmful to performance. Therefore, new strategies for task selection and assignment in MTL need to be explored. This paper studies the multi-modal, multi-task dialogue act classification task, and proposes a method for selecting and assigning tasks based on non-stationary multi-armed bandits (MAB) with discounted Thompson Sampling (TS) using Gaussian priors. Our experimental results show that in different training stages, different tasks have different utility. Our proposed method can effectively identify the task utility, actively avoid useless or harmful tasks, and realise the task assignment during training. Our proposed method is significantly superior in terms of UAR and F1 to the single-task and multi-task baselines with p-values < 0.05. Further analysis of experiments indicates that for the dataset with the data imbalance problem, our proposed method has significantly higher stability and can obtain consistent and decent performance for minority classes. Our proposed method is superior to the current state-of-the-art model.

arXiv:2308.14350공식 코드 · Papers with Code

Simple Modification of the Upper Confidence Bound Algorithm by Generalized Weighted Averages

The multi-armed bandit (MAB) problem is a classical problem that models sequential decision-making under uncertainty in reinforcement learning. In this study, we propose a new generalized upper confidence bound (UCB) algorithm (GWA-UCB1) by extending UCB1, which is a representative algorithm for MAB problems, using generalized weighted averages, and present an effective algorithm for various problem settings. GWA-UCB1 is a two-parameter generalization of the balance between exploration and exploitation in UCB1 and can be implemented with a simple modification of the UCB1 formula. Therefore, this algorithm can be easily applied to UCB-based reinforcement learning models. In preliminary experiments, we investigated the optimal parameters of a simple generalized UCB1 (G-UCB1), prepared for comparison and GWA-UCB1, in a stochastic MAB problem with two arms. Subsequently, we confirmed the performance of the algorithms with the investigated parameters on stochastic MAB problems when arm reward probabilities were sampled from uniform or normal distributions and on survival MAB problems assuming more realistic situations. GWA-UCB1 outperformed G-UCB1, UCB1-Tuned, and Thompson sampling in most problem settings and can be useful in many situations. The code is available at https://github.com/manome/python-mab.

arXiv:2308.10699공식 코드 · Papers with Code

Cost-Efficient Online Decision Making: A Combinatorial Multi-Armed Bandit Approach

Online decision making plays a crucial role in numerous real-world applications. In many scenarios, the decision is made based on performing a sequence of tests on the incoming data points. However, performing all tests can be expensive and is not always possible. In this paper, we provide a novel formulation of the online decision making problem based on combinatorial multi-armed bandits and take the (possibly stochastic) cost of performing tests into account. Based on this formulation, we provide a new framework for cost-efficient online decision making which can utilize posterior sampling or BayesUCB for exploration. We provide a theoretical analysis of Thompson Sampling for cost-efficient online decision making, and present various experimental results that demonstrate the applicability of our framework to real-world problems.

arXiv:2308.10238

Thompson Sampling for Real-Valued Combinatorial Pure Exploration of Multi-Armed Bandit

We study the real-valued combinatorial pure exploration of the multi-armed bandit (R-CPE-MAB) problem. In R-CPE-MAB, a player is given $d$ stochastic arms, and the reward of each arm $s\in\{1, \ldots, d\}$ follows an unknown distribution with mean $\mu_s$. In each time step, a player pulls a single arm and observes its reward. The player's goal is to identify the optimal \emph{action} $\boldsymbol{\pi}^{*} = \argmax_{\boldsymbol{\pi} \in \mathcal{A}} \boldsymbol{\mu}^{\top}\boldsymbol{\pi}$ from a finite-sized real-valued \emph{action set} $\mathcal{A}\subset \mathbb{R}^{d}$ with as few arm pulls as possible. Previous methods in the R-CPE-MAB assume that the size of the action set $\mathcal{A}$ is polynomial in $d$. We introduce an algorithm named the Generalized Thompson Sampling Explore (GenTS-Explore) algorithm, which is the first algorithm that can work even when the size of the action set is exponentially large in $d$. We also introduce a novel problem-dependent sample complexity lower bound of the R-CPE-MAB problem, and show that the GenTS-Explore algorithm achieves the optimal sample complexity up to a problem-dependent constant factor.

arXiv:2308.08650

AdaptEx: A Self-Service Contextual Bandit Platform

This paper presents AdaptEx, a self-service contextual bandit platform widely used at Expedia Group, that leverages multi-armed bandit algorithms to personalize user experiences at scale. AdaptEx considers the unique context of each visitor to select the optimal variants and learns quickly from every interaction they make. It offers a powerful solution to improve user experiences while minimizing the costs and time associated with traditional testing methods. The platform unlocks the ability to iterate towards optimal product solutions quickly, even in ever-changing content and continuous "cold start" situations gracefully.

arXiv:2308.01759

Bag of Policies for Distributional Deep Exploration

Efficient exploration in complex environments remains a major challenge for reinforcement learning (RL). Compared to previous Thompson sampling-inspired mechanisms that enable temporally extended exploration, i.e., deep exploration, we focus on deep exploration in distributional RL. We develop here a general purpose approach, Bag of Policies (BoP), that can be built on top of any return distribution estimator by maintaining a population of its copies. BoP consists of an ensemble of multiple heads that are updated independently. During training, each episode is controlled by only one of the heads and the collected state-action pairs are used to update all heads off-policy, leading to distinct learning signals for each head which diversify learning and behaviour. To test whether optimistic ensemble method can improve on distributional RL as did on scalar RL, by e.g. Bootstrapped DQN, we implement the BoP approach with a population of distributional actor-critics using Bayesian Distributional Policy Gradients (BDPG). The population thus approximates a posterior distribution of return distributions along with a posterior distribution of policies. Another benefit of building upon BDPG is that it allows to analyze global posterior uncertainty along with local curiosity bonus simultaneously for exploration. As BDPG is already an optimistic method, this pairing helps to investigate if optimism is accumulatable in distributional RL. Overall BoP results in greater robustness and speed during learning as demonstrated by our experimental results on ALE Atari games.

arXiv:2307.10167

VITS : Variational Inference Thompson Sampling for contextual bandits

In this paper, we introduce and analyze a variant of the Thompson sampling (TS) algorithm for contextual bandits. At each round, traditional TS requires samples from the current posterior distribution, which is usually intractable. To circumvent this issue, approximate inference techniques can be used and provide samples with distribution close to the posteriors. However, current approximate techniques yield to either poor estimation (Laplace approximation) or can be computationally expensive (MCMC methods, Ensemble sampling...). In this paper, we propose a new algorithm, Varational Inference Thompson sampling VITS, based on Gaussian Variational Inference. This scheme provides powerful posterior approximations which are easy to sample from, and is computationally efficient, making it an ideal choice for TS. In addition, we show that VITS achieves a sub-linear regret bound of the same order in the dimension and number of round as traditional TS for linear contextual bandit. Finally, we demonstrate experimentally the effectiveness of VITS on both synthetic and real world datasets.

arXiv:2307.01563

Approximate information for efficient exploration-exploitation strategies

This paper addresses the exploration-exploitation dilemma inherent in decision-making, focusing on multi-armed bandit problems. The problems involve an agent deciding whether to exploit current knowledge for immediate gains or explore new avenues for potential long-term rewards. We here introduce a novel algorithm, approximate information maximization (AIM), which employs an analytical approximation of the entropy gradient to choose which arm to pull at each point in time. AIM matches the performance of Infomax and Thompson sampling while also offering enhanced computational speed, determinism, and tractability. Empirical evaluation of AIM indicates its compliance with the Lai-Robbins asymptotic bound and demonstrates its robustness for a range of priors. Its expression is tunable, which allows for specific optimization in various settings.

arXiv:2306.17693

Thompson sampling for improved exploration in GFlowNets

Generative flow networks (GFlowNets) are amortized variational inference algorithms that treat sampling from a distribution over compositional objects as a sequential decision-making problem with a learnable action policy. Unlike other algorithms for hierarchical sampling that optimize a variational bound, GFlowNet algorithms can stably run off-policy, which can be advantageous for discovering modes of the target distribution. Despite this flexibility in the choice of behaviour policy, the optimal way of efficiently selecting trajectories for training has not yet been systematically explored. In this paper, we view the choice of trajectories for training as an active learning problem and approach it using Bayesian techniques inspired by methods for multi-armed bandits. The proposed algorithm, Thompson sampling GFlowNets (TS-GFN), maintains an approximate posterior distribution over policies and samples trajectories from this posterior for training. We show in two domains that TS-GFN yields improved exploration and thus faster convergence to the target distribution than the off-policy exploration strategies used in past work.

arXiv:2307.00863

Thompson Sampling under Bernoulli Rewards with Local Differential Privacy

This paper investigates the problem of regret minimization for multi-armed bandit (MAB) problems with local differential privacy (LDP) guarantee. Given a fixed privacy budget $\epsilon$, we consider three privatizing mechanisms under Bernoulli scenario: linear, quadratic and exponential mechanisms. Under each mechanism, we derive stochastic regret bound for Thompson Sampling algorithm. Finally, we simulate to illustrate the convergence of different mechanisms under different privacy budgets.

arXiv:2306.14872

Geometry-Aware Approaches for Balancing Performance and Theoretical Guarantees in Linear Bandits

This paper is motivated by recent research in the $d$-dimensional stochastic linear bandit literature, which has revealed an unsettling discrepancy: algorithms like Thompson sampling and Greedy demonstrate promising empirical performance, yet this contrasts with their pessimistic theoretical regret bounds. The challenge arises from the fact that while these algorithms may perform poorly in certain problem instances, they generally excel in typical instances. To address this, we propose a new data-driven technique that tracks the geometric properties of the uncertainty ellipsoid around the main problem parameter. This methodology enables us to formulate a data-driven frequentist regret bound, which incorporates the geometric information, for a broad class of base algorithms, including Greedy, OFUL, and Thompson sampling. This result allows us to identify and ``course-correct" problem instances in which the base algorithms perform poorly. The course-corrected algorithms achieve the minimax optimal regret of order $\tilde{\mathcal{O}}(d\sqrt{T})$ for a $T$-period decision-making scenario, effectively maintaining the desirable attributes of the base algorithms, including their empirical efficacy. We present simulation results to validate our findings using synthetic and real data.

arXiv:2306.14834

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.

arXiv:2306.08803

Langevin Thompson Sampling with Logarithmic Communication: Bandits and Reinforcement Learning

Thompson sampling (TS) is widely used in sequential decision making due to its ease of use and appealing empirical performance. However, many existing analytical and empirical results for TS rely on restrictive assumptions on reward distributions, such as belonging to conjugate families, which limits their applicability in realistic scenarios. Moreover, sequential decision making problems are often carried out in a batched manner, either due to the inherent nature of the problem or to serve the purpose of reducing communication and computation costs. In this work, we jointly study these problems in two popular settings, namely, stochastic multi-armed bandits (MABs) and infinite-horizon reinforcement learning (RL), where TS is used to learn the unknown reward distributions and transition dynamics, respectively. We propose batched $\textit{Langevin Thompson Sampling}$ algorithms that leverage MCMC methods to sample from approximate posteriors with only logarithmic communication costs in terms of batches. Our algorithms are computationally efficient and maintain the same order-optimal regret guarantees of $\mathcal{O}(\log T)$ for stochastic MABs, and $\mathcal{O}(\sqrt{T})$ for RL. We complement our theoretical findings with experimental results.

arXiv:2306.01990

Incentivizing Exploration with Linear Contexts and Combinatorial Actions

We advance the study of incentivized bandit exploration, in which arm choices are viewed as recommendations and are required to be Bayesian incentive compatible. Recent work has shown under certain independence assumptions that after collecting enough initial samples, the popular Thompson sampling algorithm becomes incentive compatible. We give an analog of this result for linear bandits, where the independence of the prior is replaced by a natural convexity condition. This opens up the possibility of efficient and regret-optimal incentivized exploration in high-dimensional action spaces. In the semibandit model, we also improve the sample complexity for the pre-Thompson sampling phase of initial data collection.

arXiv:2306.02574

Bayesian Learning of Optimal Policies in Markov Decision Processes with Countably Infinite State-Space

Models of many real-life applications, such as queuing models of communication networks or computing systems, have a countably infinite state-space. Algorithmic and learning procedures that have been developed to produce optimal policies mainly focus on finite state settings, and do not directly apply to these models. To overcome this lacuna, in this work we study the problem of optimal control of a family of discrete-time countable state-space Markov Decision Processes (MDPs) governed by an unknown parameter $\theta\in\Theta$, and defined on a countably-infinite state space $\mathcal X=\mathbb{Z}_+^d$, with finite action space $\mathcal A$, and an unbounded cost function. We take a Bayesian perspective with the random unknown parameter $\boldsymbol{\theta}^*$ generated via a given fixed prior distribution on $\Theta$. To optimally control the unknown MDP, we propose an algorithm based on Thompson sampling with dynamically-sized episodes: at the beginning of each episode, the posterior distribution formed via Bayes' rule is used to produce a parameter estimate, which then decides the policy applied during the episode. To ensure the stability of the Markov chain obtained by following the policy chosen for each parameter, we impose ergodicity assumptions. From this condition and using the solution of the average cost Bellman equation, we establish an $\tilde O(dh^d\sqrt{|\mathcal A|T})$ upper bound on the Bayesian regret of our algorithm, where $T$ is the time-horizon. Finally, to elucidate the applicability of our algorithm, we consider two different queuing models with unknown dynamics, and show that our algorithm can be applied to develop approximately optimal control algorithms.

arXiv:2306.01460공식 코드 · Papers with Code

ReLU to the Rescue: Improve Your On-Policy Actor-Critic with Positive Advantages

This paper proposes a step toward approximate Bayesian inference in on-policy actor-critic deep reinforcement learning. It is implemented through three changes to the Asynchronous Advantage Actor-Critic (A3C) algorithm: (1) applying a ReLU function to advantage estimates, (2) spectral normalization of actor-critic weights, and (3) incorporating \emph{dropout as a Bayesian approximation}. We prove under standard assumptions that restricting policy updates to positive advantages optimizes for value by maximizing a lower bound on the value function plus an additive term. We show that the additive term is bounded proportional to the Lipschitz constant of the value function, which offers theoretical grounding for spectral normalization of critic weights. Finally, our application of dropout corresponds to approximate Bayesian inference over both the actor and critic parameters, which enables \textit{adaptive state-aware} exploration around the modes of the actor via Thompson sampling. We demonstrate significant improvements for median and interquartile mean metrics over A3C, PPO, SAC, and TD3 on the MuJoCo continuous control benchmark and improvement over PPO in the challenging ProcGen generalization benchmark.

arXiv:2306.00242

Combinatorial Neural Bandits

We consider a contextual combinatorial bandit problem where in each round a learning agent selects a subset of arms and receives feedback on the selected arms according to their scores. The score of an arm is an unknown function of the arm's feature. Approximating this unknown score function with deep neural networks, we propose algorithms: Combinatorial Neural UCB ($\texttt{CN-UCB}$) and Combinatorial Neural Thompson Sampling ($\texttt{CN-TS}$). We prove that $\texttt{CN-UCB}$ achieves $\tilde{\mathcal{O}}(\tilde{d} \sqrt{T})$ or $\tilde{\mathcal{O}}(\sqrt{\tilde{d} T K})$ regret, where $\tilde{d}$ is the effective dimension of a neural tangent kernel matrix, $K$ is the size of a subset of arms, and $T$ is the time horizon. For $\texttt{CN-TS}$, we adapt an optimistic sampling technique to ensure the optimism of the sampled combinatorial action, achieving a worst-case (frequentist) regret of $\tilde{\mathcal{O}}(\tilde{d} \sqrt{TK})$. To the best of our knowledge, these are the first combinatorial neural bandit algorithms with regret performance guarantees. In particular, $\texttt{CN-TS}$ is the first Thompson sampling algorithm with the worst-case regret guarantees for the general contextual combinatorial bandit problem. The numerical experiments demonstrate the superior performances of our proposed algorithms.

arXiv:2305.18246공식 코드 · Papers with Code

Provable and Practical: Efficient Exploration in Reinforcement Learning via Langevin Monte Carlo

We present a scalable and effective exploration strategy based on Thompson sampling for reinforcement learning (RL). One of the key shortcomings of existing Thompson sampling algorithms is the need to perform a Gaussian approximation of the posterior distribution, which is not a good surrogate in most practical settings. We instead directly sample the Q function from its posterior distribution, by using Langevin Monte Carlo, an efficient type of Markov Chain Monte Carlo (MCMC) method. Our method only needs to perform noisy gradient descent updates to learn the exact posterior distribution of the Q function, which makes our approach easy to deploy in deep RL. We provide a rigorous theoretical analysis for the proposed method and demonstrate that, in the linear Markov decision process (linear MDP) setting, it has a regret bound of $\tilde{O}(d^{3/2}H^{3/2}\sqrt{T})$, where $d$ is the dimension of the feature mapping, $H$ is the planning horizon, and $T$ is the total number of steps. We apply this approach to deep RL, by using Adam optimizer to perform gradient updates. Our approach achieves better or similar results compared with state-of-the-art deep RL algorithms on several challenging exploration tasks from the Atari57 suite.

arXiv:2305.14704

Practical Batch Bayesian Sampling Algorithms for Online Adaptive Traffic Experimentation

Online controlled experiments have emerged as industry gold standard for assessing new web features. As new web algorithms proliferate, experimentation platform faces an increasing demand on the velocity of online experiments, which encourages adaptive traffic testing methods to speed up identifying best variant by efficiently allocating traffic. This paper proposed four Bayesian batch bandit algorithms (NB-TS, WB-TS, NB-TTTS, WB-TTTS) for eBay's experimentation platform, using summary batch statistics of a goal metric without incurring new engineering technical debts. The novel WB-TTTS, in particular, demonstrates as an efficient, trustworthy and robust alternative to fixed horizon A/B testing. Another novel contribution is to bring trustworthiness of best arm identification algorithms into evaluation criterion and highlight the existence of severe false positive inflation with equivalent best arms. To gain the trust of experimenters, experimentation platform must consider both efficiency and trustworthiness; However, to the best of authors' knowledge, trustworthiness as an important topic is rarely discussed. This paper shows that Bayesian bandits without neutral posterior reshaping, particularly naive Thompson sampling (NB-TS), are untrustworthy because they can always identify an arm as the best from equivalent best arms. To restore trustworthiness, a novel finding uncovers connections between convergence distribution of posterior optimal probabilities of equivalent best arms and neutral posterior reshaping, which controls false positives. Lastly, this paper presents lessons learned from eBay's experience, as well as thorough evaluations. We hope this work is useful to other industrial practitioners and inspires academic researchers interested in the trustworthiness of adaptive traffic experimentation.

arXiv:2305.11908

Sequential Best-Arm Identification with Application to Brain-Computer Interface

A brain-computer interface (BCI) is a technology that enables direct communication between the brain and an external device or computer system. It allows individuals to interact with the device using only their thoughts, and holds immense potential for a wide range of applications in medicine, rehabilitation, and human augmentation. An electroencephalogram (EEG) and event-related potential (ERP)-based speller system is a type of BCI that allows users to spell words without using a physical keyboard, but instead by recording and interpreting brain signals under different stimulus presentation paradigms. Conventional non-adaptive paradigms treat each word selection independently, leading to a lengthy learning process. To improve the sampling efficiency, we cast the problem as a sequence of best-arm identification tasks in multi-armed bandits. Leveraging pre-trained large language models (LLMs), we utilize the prior knowledge learned from previous tasks to inform and facilitate subsequent tasks. To do so in a coherent way, we propose a sequential top-two Thompson sampling (STTS) algorithm under the fixed-confidence setting and the fixed-budget setting. We study the theoretical property of the proposed algorithm, and demonstrate its substantial empirical improvement through both synthetic data analysis as well as a P300 BCI speller simulator example.