Multiplayer Multi-armed Bandits for Optimal Assignment in Heterogeneous Networks

Tibrewal, Harshvardhan; Patchala, Sravan; Hanawal, Manjesh K.; Darak, Sumit J.

doi:10.48550/arxiv.1901.03868

Cited by 8 publications

(22 citation statements)

References 0 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The simplest approach to solve the spectrum collaboration problem in ad-hoc networks is sharing CSI between nodes, thereby reducing the problem back to its centralized form. This approach is taken in [6] and [7] for stationary channels and in [8], [9] and [10] for dynamic channels. Tibrewal et.…”

Section: A Quasi-centralized Algorithmsmentioning

confidence: 99%

“…al. [6] used carrier-sensing. This facilitated the gathering of all CSI in every node where the Hungarian Algorithm was applied to find the optimal allocation.…”

Section: A Quasi-centralized Algorithmsmentioning

confidence: 99%

“…Therefore, signaling between users become more costly. Hence, rather than collecting the CSI in every node like in [6], in [7] the CSI was gathered only in a single Leader node.…”

Section: A Quasi-centralized Algorithmsmentioning

confidence: 99%

“…Rather than using the Hungarian Algorithm as in [6], the Leader node in [7] applies a matching elimination algorithm and signals its results to all other users. The matching elimination algorithm proceeds by eliminating edges from the bipartite graph representing the resource allocation problem.…”

Section: A Quasi-centralized Algorithmsmentioning

confidence: 99%

“…Zylinium modeled the problem as a mixed integer programming problem and solved it with Google's OR-Tools library [16]. While in theory the regrets of [6], [7], [8], [9] and [10] are attractively close to their respective lower bounds, in practice the signaling of CSI results in significant overhead and these methods do not scale well. Furthermore, leader election is non-robust especially in mobile ad-hoc networks -if the leader is jammed or becomes disconnected due to mobility.These problems, suggest that a more robust fully distributed solution might be the way to achieve robust spectrum sharing.…”

Section: A Quasi-centralized Algorithmsmentioning

confidence: 99%

See 4 more Smart Citations

Medium Access Control protocol for Collaborative Spectrum Learning in Wireless Networks

Boyarski¹,

Leshem²

2021

Preprint

View full text Add to dashboard Cite

In recent years there is a growing effort to provide learning algorithms for spectrum collaboration. In this paper we present a medium access control protocol which alllows spectrum collaboration with minimal regret and high spectral efficiency in highly loaded networks. We present a fully-distributed algorithm for spectrum collaboration in congested ad-hoc networks. The algorithm jointly solves both the channel allocation and access scheduling problems. We prove that the algorithm has an optimal logarithmic regret. Based on the algorithm we provide a medium access control protocol which allows distributed implementation of the algorithm in ad-hoc networks. The protocol utilizes single-channel opportunistic carrier sensing to carry out a lowcomplexity distributed auction in time and frequency. We also discuss practical implementation issues such as bounded frame size and speed of convergence. Computer simulations comparing the algorithm to state-of-the-art distributed medium access control protocols show the significant advantage of the proposed scheme.

show abstract

Section: A Quasi-centralized Algorithmsmentioning

confidence: 99%

“…al. [6] used carrier-sensing. This facilitated the gathering of all CSI in every node where the Hungarian Algorithm was applied to find the optimal allocation.…”

Section: A Quasi-centralized Algorithmsmentioning

confidence: 99%

“…Therefore, signaling between users become more costly. Hence, rather than collecting the CSI in every node like in [6], in [7] the CSI was gathered only in a single Leader node.…”

Section: A Quasi-centralized Algorithmsmentioning

confidence: 99%

Section: A Quasi-centralized Algorithmsmentioning

confidence: 99%

Section: A Quasi-centralized Algorithmsmentioning

confidence: 99%

See 3 more Smart Citations

Medium Access Control protocol for Collaborative Spectrum Learning in Wireless Networks

Boyarski¹,

Leshem²

2021

Preprint

View full text Add to dashboard Cite

show abstract

Decentralized Stochastic Multi-Player Multi-Armed Walking Bandits

Xiong

2023

AAAI

View full text Add to dashboard Cite

Multi-player multi-armed bandit is an increasingly relevant decision-making problem, motivated by applications to cognitive radio systems. Most research for this problem focuses exclusively on the settings that players have full access to all arms and receive no reward when pulling the same arm. Hence all players solve the same bandit problem with the goal of maximizing their cumulative reward. However, these settings neglect several important factors in many real-world applications, where players have limited access to a dynamic local subset of arms (i.e., an arm could sometimes be ``walking'' and not accessible to the player). To this end, this paper proposes a multi-player multi-armed walking bandits model, aiming to address aforementioned modeling issues. The goal now is to maximize the reward, however, players can only pull arms from the local subset and only collect a full reward if no other players pull the same arm. We adopt Upper Confidence Bound (UCB) to deal with the exploration-exploitation tradeoff and employ distributed optimization techniques to properly handle collisions. By carefully integrating these two techniques, we propose a decentralized algorithm with near-optimal guarantee on the regret, and can be easily implemented to obtain competitive empirical performance.

show abstract

Decentralized Scheduling with QoS Constraints: Achieving O(1) QoS Regret of Multi-Player Bandits

Liu,

Fang

2024

AAAI

View full text Add to dashboard Cite

We consider a decentralized multi-player multi-armed bandit (MP-MAB) problem where players cannot observe the actions and rewards of other players and no explicit communication or coordination between players is possible. Prior studies mostly focus on maximizing the sum of rewards of the players over time. However, the total reward maximization learning may lead to imbalanced reward among players, leading to poor Quality of Service (QoS) for some players. In contrast, our objective is to let each player n achieve a predetermined expected average reward over time, i.e., achieving a predetermined level of QoS. We develop a novel decentralized MP-MAB algorithm to accomplish this objective by leveraging the methodology of randomized matching. We prove that our decentralized algorithm can ensure that all players have an O(1) QoS regret. We also reveal an analog between our MP-MAB model and the online wireless queuing systems, which builds a connection between QoS in MP-MAB learning and stability in queuing theory.

show abstract

Multiplayer Multi-armed Bandits for Optimal Assignment in Heterogeneous Networks

Cited by 8 publications

References 0 publications

Medium Access Control protocol for Collaborative Spectrum Learning in Wireless Networks

Medium Access Control protocol for Collaborative Spectrum Learning in Wireless Networks

Decentralized Stochastic Multi-Player Multi-Armed Walking Bandits

Decentralized Scheduling with QoS Constraints: Achieving O(1) QoS Regret of Multi-Player Bandits

Contact Info

Product

Resources

About