Cooperative and Stochastic Multi-Player Multi-Armed Bandit: Optimal Regret With Neither Communication Nor Collisions

• URL: http://arxiv.org/abs/2011.03896v1
• Date: Sun, 8 Nov 2020 03:14:19 GMT
• Title: Cooperative and Stochastic Multi-Player Multi-Armed Bandit: Optimal Regret With Neither Communication Nor Collisions
• Authors: S\'ebastien Bubeck, Thomas Budzinski, Mark Sellke
• Abstract summary: We consider the cooperative multi-player version of the multi-armed bandit problem. We show that these properties are achievable for any number of players and arms.
• Score: 4.974932889340056
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: We consider the cooperative multi-player version of the stochastic multi-armed bandit problem. We study the regime where the players cannot communicate but have access to shared randomness. In prior work by the first two authors, a strategy for this regime was constructed for two players and three arms, with regret $\tilde{O}(\sqrt{T})$, and with no collisions at all between the players (with very high probability). In this paper we show that these properties (near-optimal regret and no collisions at all) are achievable for any number of players and arms. At a high level, the previous strategy heavily relied on a $2$-dimensional geometric intuition that was difficult to generalize in higher dimensions, while here we take a more combinatorial route to build the new strategy.

Related papers

• Multi-Player Approaches for Dueling Bandits [58.442742345319225]
  We show that the direct use of a Follow Your Leader black-box approach matches the lower bound for this setting. We also analyze a message-passing fully distributed approach with a novel Condorcet-winner recommendation protocol.
  arXiv  Detail & Related papers  (2024-05-25T10:25:48Z)
• Leading the Pack: N-player Opponent Shaping [52.682734939786464]
  We extend Opponent Shaping (OS) methods to environments involving multiple co-players and multiple shaping agents. We find that when playing with a large number of co-players, OS methods' relative performance reduces, suggesting that in the limit OS methods may not perform well.
  arXiv  Detail & Related papers  (2023-12-19T20:01:42Z)
• Decentralized Stochastic Multi-Player Multi-Armed Walking Bandits [6.732901486505047]
  Multi-player multi-armed bandit is an increasingly relevant decision-making problem, motivated by applications to cognitive radio systems. This paper proposes a textitmulti-player multi-armed walking bandits model, aiming to address aforementioned modeling issues.
  arXiv  Detail & Related papers  (2022-12-12T23:26:02Z)
• Provably Efficient Fictitious Play Policy Optimization for Zero-Sum Markov Games with Structured Transitions [145.54544979467872]
  We propose and analyze new fictitious play policy optimization algorithms for zero-sum Markov games with structured but unknown transitions. We prove tight $widetildemathcalO(sqrtK)$ regret bounds after $K$ episodes in a two-agent competitive game scenario. Our algorithms feature a combination of Upper Confidence Bound (UCB)-type optimism and fictitious play under the scope of simultaneous policy optimization.
  arXiv  Detail & Related papers  (2022-07-25T18:29:16Z)
• The Pareto Frontier of Instance-Dependent Guarantees in Multi-Player Multi-Armed Bandits with no Communication [10.446001329147112]
  We study the multi-player multi-armed bandit problem. In this problem, $m$ players cooperate to maximize their total reward from $K > m$ arms. We ask whether it is possible to obtain optimal instance-dependent regret $tildeO (1/Delta)$ where $Delta$ is the gap between the $m$-th and $m+1$-st best arms.
  arXiv  Detail & Related papers  (2022-02-19T18:19:36Z)
• An Instance-Dependent Analysis for the Cooperative Multi-Player Multi-Armed Bandit [93.97385339354318]
  We study the problem of information sharing and cooperation in Multi-Player Multi-Armed bandits. First, we show that a simple modification to a successive elimination strategy can be used to allow the players to estimate their suboptimality gaps. Second, we leverage the first result to design a communication protocol that successfully uses the small reward of collisions to coordinate among players.
  arXiv  Detail & Related papers  (2021-11-08T23:38:47Z)
• Bandit Learning in Decentralized Matching Markets [82.39061186055775]
  We study two-sided matching markets in which one side of the market (the players) does not have a priori knowledge about its preferences for the other side (the arms) and is required to learn its preferences from experience. This model extends the standard multi-armed bandit framework to a decentralized multiple player setting with competition. We show that the algorithm is incentive compatible whenever the arms' preferences are shared, but not necessarily so when preferences are fully general.
  arXiv  Detail & Related papers  (2020-12-14T08:58:07Z)
• Multitask Bandit Learning Through Heterogeneous Feedback Aggregation [35.923544685900055]
  We formulate the problem as the $epsilon$-multi-player multi-armed bandit problem, in which a set of players concurrently interact with a set of arms. We develop an upper confidence bound-based algorithm, RobustAgg$(epsilon)$, that adaptively aggregates rewards collected by different players.
  arXiv  Detail & Related papers  (2020-10-29T07:13:28Z)
• Faster Algorithms for Optimal Ex-Ante Coordinated Collusive Strategies in Extensive-Form Zero-Sum Games [123.76716667704625]
  We focus on the problem of finding an optimal strategy for a team of two players that faces an opponent in an imperfect-information zero-sum extensive-form game. In that setting, it is known that the best the team can do is sample a profile of potentially randomized strategies (one per player) from a joint (a.k.a. correlated) probability distribution at the beginning of the game. We provide an algorithm that computes such an optimal distribution by only using profiles where only one of the team members gets to randomize in each profile.
  arXiv  Detail & Related papers  (2020-09-21T17:51:57Z)
• Coordination without communication: optimal regret in two players multi-armed bandits [1.6752182911522522]
  We consider two agents playing simultaneously the same three-armed bandit problem. We propose a strategy with no collisions at all between the players. We also argue that the extra logarithmic term $sqrtlog(T)$ should be necessary by proving a lower bound for a full information variant of the problem.
  arXiv  Detail & Related papers  (2020-02-14T17:35:42Z)
• Selfish Robustness and Equilibria in Multi-Player Bandits [25.67398941667429]
  In a game, several players simultaneously pull arms and encounter a collision - with 0 reward - if some of them pull the same arm at the same time. While the cooperative case where players maximize the collective reward has been mostly considered, to malicious players is a crucial and challenging concern. We shall consider instead the more natural class of selfish players whose incentives are to maximize their individual rewards, potentially at the expense of the social welfare.
  arXiv  Detail & Related papers  (2020-02-04T09:50:28Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.