RL in Markov Games with Independent Function Approximation: Improved Sample Complexity Bound under the Local Access Model

Efficiently learning equilibria with large state and action spaces in general-sum Markov games while overcoming the curse of multi-agency is a challenging problem. Recent works have attempted to solve this problem by employing independent linear function classes to approximate the marginal $Q$-value for each agent. However, existing sample complexity bounds under such a framework have a suboptimal dependency on the desired accuracy $\varepsilon$ or the action space. In this work, we introduce a new algorithm, Lin-Confident-FTRL, for learning coarse correlated equilibria (CCE) with local access to the simulator, i.e., one can interact with the underlying environment on the visited states. Up to a logarithmic dependence on the size of the state space, Lin-Confident-FTRL learns $\epsilon$-CCE with a provable optimal accuracy bound $O(\epsilon^{-2})$ and gets rids of the linear dependency on the action space, while scaling polynomially with relevant problem parameters (such as the number of agents and time horizon). Moreover, our analysis of Linear-Confident-FTRL generalizes the virtual policy iteration technique in the single-agent local planning literature, which yields a new computationally efficient algorithm with a tighter sample complexity bound when assuming random access to the simulator.

Stochastic Graph Bandit Learning with Side-Observations

In this paper, we investigate the stochastic contextual bandit with general function space and graph feedback. We propose an algorithm that addresses this problem by adapting to both the underlying graph structures and reward gaps. To the best of our knowledge, our algorithm is the first to provide a gap-dependent upper bound in this stochastic setting, bridging the research gap left by the work in [35]. In comparison to [31,33,35], our method offers improved regret upper bounds and does not require knowledge of graphical quantities. We conduct numerical experiments to demonstrate the computational efficiency and effectiveness of our approach in terms of regret upper bounds. These findings highlight the significance of our algorithm in advancing the field of stochastic contextual bandits with graph feedback, opening up avenues for practical applications in various domains.

Provably Efficient Learning in Partially Observable Contextual Bandit

In this paper, we investigate transfer learning in partially observable contextual bandits, where agents have limited knowledge from other agents and partial information about hidden confounders. We first convert the problem to identifying or partially identifying causal effects between actions and rewards through optimization problems. To solve these optimization problems, we discretize the original functional constraints of unknown distributions into linear constraints, and sample compatible causal models via sequentially solving linear programmings to obtain causal bounds with the consideration of estimation error. Our sampling algorithms provide desirable convergence results for suitable sampling distributions. We then show how causal bounds can be applied to improving classical bandit algorithms and affect the regrets with respect to the size of action sets and function spaces. Notably, in the task with function approximation which allows us to handle general context distributions, our method improves the order dependence on function space size compared with previous literatures. We formally prove that our causally enhanced algorithms outperform classical bandit algorithms and achieve orders of magnitude faster convergence rates. Finally, we perform simulations that demonstrate the efficiency of our strategy compared to the current state-of-the-art methods. This research has the potential to enhance the performance of contextual bandit agents in real-world applications where data is scarce and costly to obtain.

Debiasing Recommendation by Learning Identifiable Latent Confounders

Recommendation systems aim to predict users' feedback on items not exposed to them. Confounding bias arises due to the presence of unmeasured variables (e.g., the socio-economic status of a user) that can affect both a user's exposure and feedback. Existing methods either (1) make untenable assumptions about these unmeasured variables or (2) directly infer latent confounders from users' exposure. However, they cannot guarantee the identification of counterfactual feedback, which can lead to biased predictions. In this work, we propose a novel method, i.e., identifiable deconfounder (iDCF), which leverages a set of proxy variables (e.g., observed user features) to resolve the aforementioned non-identification issue. The proposed iDCF is a general deconfounded recommendation framework that applies proximal causal inference to infer the unmeasured confounders and identify the counterfactual feedback with theoretical guarantees. Extensive experiments on various real-world and synthetic datasets verify the proposed method's effectiveness and robustness.

Single-Trajectory Distributionally Robust Reinforcement Learning

As a framework for sequential decision-making, Reinforcement Learning (RL) has been regarded as an essential component leading to Artificial General Intelligence (AGI). However, RL is often criticized for having the same training environment as the test one, which also hinders its application in the real world. To mitigate this problem, Distributionally Robust RL (DRRL) is proposed to improve the worst performance in a set of environments that may contain the unknown test environment. Due to the nonlinearity of the robustness goal, most of the previous work resort to the model-based approach, learning with either an empirical distribution learned from the data or a simulator that can be sampled infinitely, which limits their applications in simple dynamics environments. In contrast, we attempt to design a DRRL algorithm that can be trained along a single trajectory, i.e., no repeated sampling from a state. Based on the standard Q-learning, we propose distributionally robust Q-learning with the single trajectory (DRQ) and its average-reward variant named differential DRQ. We provide asymptotic convergence guarantees and experiments for both settings, demonstrating their superiority in the perturbed environments against the non-robust ones.

Distributionally Robust Offline Reinforcement Learning with Linear Function Approximation

Among the reasons hindering reinforcement learning (RL) applications to real-world problems, two factors are critical: limited data and the mismatch between the testing environment (real environment in which the policy is deployed) and the training environment (e.g., a simulator). This paper attempts to address these issues simultaneously with distributionally robust offline RL, where we learn a distributionally robust policy using historical data obtained from the source environment by optimizing against a worst-case perturbation thereof. In particular, we move beyond tabular settings and consider linear function approximation. More specifically, we consider two settings, one where the dataset is well-explored and the other where the dataset has sufficient coverage. We propose two algorithms -- one for each of the two settings -- that achieve error bounds $\tilde{O}(d^{1/2}/N^{1/2})$ and $\tilde{O}(d^{3/2}/N^{1/2})$ respectively, where $d$ is the dimension in the linear function approximation and $N$ is the number of trajectories in the dataset. To the best of our knowledge, they provide the first non-asymptotic results of the sample complexity in this setting. Diverse experiments are conducted to demonstrate our theoretical findings, showing the superiority of our algorithm against the non-robust one.

Dual Instrumental Method for Confounded Kernelized Bandits

The contextual bandit problem is a theoretically justified framework with wide applications in various fields. While the previous study on this problem usually requires independence between noise and contexts, our work considers a more sensible setting where the noise becomes a latent confounder that affects both contexts and rewards. Such a confounded setting is more realistic and could expand to a broader range of applications. However, the unresolved confounder will cause a bias in reward function estimation and thus lead to a large regret. To deal with the challenges brought by the confounder, we apply the dual instrumental variable regression, which can correctly identify the true reward function. We prove the convergence rate of this method is near-optimal in two types of widely used reproducing kernel Hilbert spaces. Therefore, we can design computationally efficient and regret-optimal algorithms based on the theoretical guarantees for confounded bandit problems. The numerical results illustrate the efficacy of our proposed algorithms in the confounded bandit setting.

On Private Online Convex Optimization: Optimal Algorithms in $\ell_p$-Geometry and High Dimensional Contextual Bandits

Differentially private (DP) stochastic convex optimization (SCO) is ubiquitous in trustworthy machine learning algorithm design. This paper studies the DP-SCO problem with streaming data sampled from a distribution and arrives sequentially. We also consider the continual release model where parameters related to private information are updated and released upon each new data, often known as the online algorithms. Despite that numerous algorithms have been developed to achieve the optimal excess risks in different $\ell_p$ norm geometries, yet none of the existing ones can be adapted to the streaming and continual release setting. To address such a challenge as the online convex optimization with privacy protection, we propose a private variant of online Frank-Wolfe algorithm with recursive gradients for variance reduction to update and reveal the parameters upon each data. Combined with the adaptive differential privacy analysis, our online algorithm achieves in linear time the optimal excess risk when $1<p\leq 2$ and the state-of-the-art excess risk meeting the non-private lower ones when $2<p\leq\infty$. Our algorithm can also be extended to the case $p=1$ to achieve nearly dimension-independent excess risk. While previous variance reduction results on recursive gradient have theoretical guarantee only in the independent and identically distributed sample setting, we establish such a guarantee in a non-stationary setting. To demonstrate the virtues of our method, we design the first DP algorithm for high-dimensional generalized linear bandits with logarithmic regret. Comparative experiments with a variety of DP-SCO and DP-Bandit algorithms exhibit the efficacy and utility of the proposed algorithms.

Generalized Linear Bandits with Local Differential Privacy

Contextual bandit algorithms are useful in personalized online decision-making. However, many applications such as personalized medicine and online advertising require the utilization of individual-specific information for effective learning, while user's data should remain private from the server due to privacy concerns. This motivates the introduction of local differential privacy (LDP), a stringent notion in privacy, to contextual bandits. In this paper, we design LDP algorithms for stochastic generalized linear bandits to achieve the same regret bound as in non-privacy settings. Our main idea is to develop a stochastic gradient-based estimator and update mechanism to ensure LDP. We then exploit the flexibility of stochastic gradient descent (SGD), whose theoretical guarantee for bandit problems is rarely explored, in dealing with generalized linear bandits. We also develop an estimator and update mechanism based on Ordinary Least Square (OLS) for linear bandits. Finally, we conduct experiments with both simulation and real-world datasets to demonstrate the consistently superb performance of our algorithms under LDP constraints with reasonably small parameters $(\varepsilon, \delta)$ to ensure strong privacy protection.