More Like this

1. Federated Bandit: A Gossiping Approach

   https://doi.org/10.1145/3447380  

   Zhu, Zhaowei ; Zhu, Jingxuan ; Liu, Ji ; Liu, Yang ( February 2021 , Proceedings of the ACM on Measurement and Analysis of Computing Systems)

   null (Ed.)

   In this paper, we study Federated Bandit, a decentralized Multi-Armed Bandit problem with a set of N agents, who can only communicate their local data with neighbors described by a connected graph G. Each agent makes a sequence of decisions on selecting an arm from M candidates, yet they only have access to local and potentially biased feedback/evaluation of the true reward for each action taken. Learning only locally will lead agents to sub-optimal actions while converging to a no-regret strategy requires a collection of distributed data. Motivated by the proposal of federated learning, we aim for a solution with which agents will never share their local observations with a central entity, and will be allowed to only share a private copy of his/her own information with their neighbors. We first propose a decentralized bandit algorithm \textttGossip\_UCB, which is a coupling of variants of both the classical gossiping algorithm and the celebrated Upper Confidence Bound (UCB) bandit algorithm. We show that \textttGossip\_UCB successfully adapts local bandit learning into a global gossiping process for sharing information among connected agents, and achieves guaranteed regret at the order of O(\max\ \textttpoly (N,M) łog T, \textttpoly (N,M)łog_łambda_2^-1 N\ ) for all N agents, where łambda_2\in(0,1) is the second largest eigenvalue of the expected gossip matrix, which is a function of G. We then propose \textttFed\_UCB, a differentially private version of \textttGossip\_UCB, in which the agents preserve ε-differential privacy of their local data while achieving O(\max \\frac\textttpoly (N,M) ε łog^2.5 T, \textttpoly (N,M) (łog_łambda_2^-1 N + łog T) \ ) regret. 

   more » « less
2. MDPGT: Momentum-Based Decentralized Policy Gradient Tracking

   https://doi.org/10.1609/aaai.v36i9.21169  

   Jiang, Zhanhong ; Lee, Xian Yeow ; Tan, Sin Yong ; Tan, Kai Liang ; Balu, Aditya ; Lee, Young M ; Hegde, Chinmay ; Sarkar, Soumik ( June 2022 , Proceedings of the AAAI Conference on Artificial Intelligence)

   We propose a novel policy gradient method for multi-agent reinforcement learning, which leverages two different variance-reduction techniques and does not require large batches over iterations. Specifically, we propose a momentum-based decentralized policy gradient tracking (MDPGT) where a new momentum-based variance reduction technique is used to approximate the local policy gradient surrogate with importance sampling, and an intermediate parameter is adopted to track two consecutive policy gradient surrogates. MDPGT provably achieves the best available sample complexity of O(N -1 e -3) for converging to an e-stationary point of the global average of N local performance functions (possibly nonconcave). This outperforms the state-of-the-art sample complexity in decentralized model-free reinforcement learning and when initialized with a single trajectory, the sample complexity matches those obtained by the existing decentralized policy gradient methods. We further validate the theoretical claim for the Gaussian policy function. When the required error tolerance e is small enough, MDPGT leads to a linear speed up, which has been previously established in decentralized stochastic optimization, but not for reinforcement learning. Lastly, we provide empirical results on a multi-agent reinforcement learning benchmark environment to support our theoretical findings. 

   more » « less
3. (Private) Kernelized Bandits with Distributed Biased Feedback

   https://doi.org/10.1145/3579318  

   Li, Fengjiao ; Zhou, Xingyu ; Ji, Bo ( February 2023 , Proceedings of the ACM on Measurement and Analysis of Computing Systems)

   In this paper, we study kernelized bandits with distributed biased feedback. This problem is motivated by several real-world applications (such as dynamic pricing, cellular network configuration, and policy making), where users from a large population contribute to the reward of the action chosen by a central entity, but it is difficult to collect feedback from all users. Instead, only biased feedback (due to user heterogeneity) from a subset of users may be available. In addition to such partial biased feedback, we are also faced with two practical challenges due to communication cost and computation complexity. To tackle these challenges, we carefully design a new distributed phase-then-batch-based elimination (DPBE) algorithm, which samples users in phases for collecting feedback to reduce the bias and employs maximum variance reduction to select actions in batches within each phase. By properly choosing the phase length, the batch size, and the confidence width used for eliminating suboptimal actions, we show that DPBE achieves a sublinear regret of ~O(T1-α/2 +√γT T), where α ∈ (0,1) is the user-sampling parameter one can tune. Moreover, DPBE can significantly reduce both communication cost and computation complexity in distributed kernelized bandits, compared to some variants of the state-of-the-art algorithms (originally developed for standard kernelized bandits). Furthermore, by incorporating various differential privacy models (including the central, local, and shuffle models), we generalize DPBE to provide privacy guarantees for users participating in the distributed learning process. Finally, we conduct extensive simulations to validate our theoretical results and evaluate the empirical performance. 

   more » « less
4. Learning a Decentralized Multi-arm Motion Planner

   Ha, Huy ; Xu, Jingxi ; Song, Shuran ( November 2020 , Proceedings of the 2020 Conference on Robot Learning)

   We present a closed-loop multi-arm motion planner that is scalable and flexible with team size. Traditional multi-arm robotic systems have relied on centralized motion planners, whose run times often scale exponentially with team size, and thus, fail to handle dynamic environments with open-loop control. In this paper, we tackle this problem with multi-agent reinforcement learning, where a shared policy network is trained to control each individual robot arm to reach its target end-effector pose given observations of its workspace state and target end-effector pose. The policy is trained using Soft Actor-Critic with expert demonstrations from a sampling-based motion planning algorithm (i.e., BiRRT). By leveraging classical planning algorithms, we can improve the learning efficiency of the reinforcement learning algorithm while retaining the fast inference time of neural networks. The resulting policy scales sub-linearly and can be deployed on multi-arm systems with variable team sizes. Thanks to the closed-loop and decentralized formulation, our approach generalizes to 5-10 multiarm systems and dynamic moving targets (>90% success rate for a 10-arm system), despite being trained on only 1-4 arm planning tasks with static targets. 

   more » « less
5. Distributed Q-Learning with State Tracking for Multi-agent Networked Control

   Wang, Hang ; Lin, Sen ; Jafarkhani, Hamid ; Zhang, Junshan ( May 2021 , AAMAS '21: Proceedings of the 20th International Conference on Autonomous Agents and MultiAgent SystemsMay 2021)

   This paper studies distributed Q-learning for Linear Quadratic Regulator (LQR) in a multi-agent network. The existing results often assume that agents can observe the global system state, which may be infeasible in large-scale systems due to privacy concerns or communication constraints. In this work, we consider a setting with unknown system models and no centralized coordinator. We devise a state tracking (ST) based Q-learning algorithm to design optimal controllers for agents. Specifically, we assume that agents maintain local estimates of the global state based on their local information and communications with neighbors. At each step, every agent updates its local global state estimation, based on which it solves an approximate Q-factor locally through policy iteration. Assuming a decaying injected excitation noise during the policy evaluation, we prove that the local estimation converges to the true global state, and establish the convergence of the proposed distributed ST-based Q-learning algorithm. The experimental studies corroborate our theoretical results by showing that our proposed method achieves comparable performance with the centralized case. 

   more » « less