An official website of the United States government
We study the cooperative asynchronous multi-agent multi-armed bandits problem, where each agent's active (arm pulling) decision rounds are asynchronous. That is, in each round, only a subset of agents is active to pull arms, and this subset is unknown and time-varying. We consider two models of multi-agent cooperation, fully distributed and leader-coordinated, and propose algorithms for both models that attain near-optimal regret and communications bounds, both of which are almost as good as their synchronous counterparts. The fully distributed algorithm relies on a novel communication policy consisting of accuracy adaptive and on-demand components, and successive arm elimination for decision-making. For leader-coordinated algorithms, a single leader explores arms and recommends them to other agents (followers) to exploit. As agents' active rounds are unknown, a competent leader must be chosen dynamically. We propose a variant of the Tsallis-INF algorithm with low switches to choose such a leader sequence. Lastly, we report numerical simulations of our new asynchronous algorithms with other known baselines.
more »
« less
Bandit Algorithms for Prophet Inequality and Pandora's Box
The Prophet Inequality and Pandora's Box problems are fundamental stochastic problem with applications in Mechanism Design, Online Algorithms, Stochastic Optimization, Optimal Stopping, and Operations Research. A usual assumption in these works is that the probability distributions of the n underlying random variables are given as input to the algorithm. Since in practice these distributions need to be learned under limited feedback, we initiate the study of such stochastic problems in the Multi-Armed Bandits model. In the Multi-Armed Bandits model we interact with n unknown distributions over T rounds: in round t we play a policy x(t) and only receive the value of x(t) as feedback. The goal is to minimize the regret, which is the difference over T rounds in the total value of the optimal algorithm that knows the distributions vs. the total value of our algorithm that learns the distributions from the limited feedback. Our main results give near-optimal Õ (poly (n) √T) total regret algorithms for both Prophet Inequality and Pandora's Box. Our proofs proceed by maintaining confidence intervals on the unknown indices of the optimal policy. The exploration-exploitation tradeoff prevents us from directly refining these confidence intervals, so the main technique is to design a regret upper bound function that is learnable while playing low-regret Bandit policies.
more »
« less
- Award ID(s):
- 2327010
- PAR ID:
- 10538688
- Publisher / Repository:
- SIAM
- Date Published:
- ISBN:
- 978-1-61197-791-2
- Format(s):
- Medium: X
- Location:
- Alexandria, VA, USA
- Sponsoring Org:
- National Science Foundation
More Like this
-
-
We investigate learning the equilibria in non-stationary multi-agent systems and address the challenges that differentiate multi-agent learning from single-agent learning. Specifically, we focus on games with bandit feedback, where testing an equilibrium can result in substantial regret even when the gap to be tested is small, and the existence of multiple optimal solutions (equilibria) in stationary games poses extra challenges. To overcome these obstacles, we propose a versatile black-box approach applicable to a broad spectrum of problems, such as general-sum games, potential games, and Markov games, when equipped with appropriate learning and testing oracles for stationary environments. Our algorithms can achieve O(∆^1/4 T^3/4) regret when the degree of nonstationarity, as measured by total variation ∆, is known, and O(∆^1/5 T^4/5) regret when ∆ is unknown, where T is the number of rounds. Meanwhile, our algorithm inherits the favorable dependence on number of agents from the oracles. As a side contribution that may be independent of interest, we show how to test for various types of equilibria by a black-box reduction to single-agent learning, which includes Nash equilibria, correlated equilibria, and coarse correlated equilibria.more » « less
-
Banerjee, Arindam; Fukumizu, Kenji (Ed.)We study a constrained contextual linear bandit setting, where the goal of the agent is to produce a sequence of policies, whose expected cumulative reward over the course of multiple rounds is maximum, and each one of them has an expected cost below a certain threshold. We propose an upper-confidence bound algorithm for this problem, called optimistic pessimistic linear bandit (OPLB), and prove a sublinear bound on its regret that is inversely proportional to the difference between the constraint threshold and the cost of a known feasible action. Our algorithm balances exploration and constraint satisfaction using a novel idea that scales the radii of the reward and cost confidence sets with different scaling factors. We further specialize our results to multi-armed bandits and propose a computationally efficient algorithm for this setting and prove a a regret bound that is better than simply casting multi-armed bandits as an instance of linear bandits and using the regret bound of OPLB. We also prove a lower-bound for the problem studied in the paper and provide simulations to validate our theoretical results. Finally, we show how our algorithm and analysis can be extended to multiple constraints and to the case when the cost of the feasible action is unknown.more » « less
-
Considerable work has focused on optimal stopping problems where random IID offers arrive sequentially for a single available resource which is controlled by the decision-maker. After viewing the realization of the offer, the decision-maker irrevocably rejects it, or accepts it, collecting the reward and ending the game. We consider an important extension of this model to a dynamic setting where the resource is "renewable'' (a rental, a work assignment, or a temporary position) and can be allocated again after a delay period d. In the case where the reward distribution is known a priori, we design an (asymptotically optimal) 1/2-competitive Prophet Inequality, namely, a policy that collects in expectation at least half of the expected reward collected by a prophet who a priori knows all the realizations. This policy has a particularly simple characterization as a thresholding rule which depends on the reward distribution and the blocking period d, and arises naturally from an LP-relaxation of the prophet's optimal solution. Moreover, it gives the key for extending to the case of unknown distributions; here, we construct a dynamic threshold rule using the reward samples collected when the resource is not blocked. We provide a regret guarantee for our algorithm against the best policy in hindsight, and prove a complementing minimax lower bound on the best achievable regret, establishing that our policy achieves, up to poly-logarithmic factors, the best possible regret in this setting.more » « less
-
One of the primary challenges in large-scale distributed learning stems from stringent communication constraints. While several recent works address this challenge for static optimization problems, sequential decision-making under uncertainty has remained much less explored in this regard. Motivated by this gap, we introduce a new linear stochastic bandit formulation over a bit-constrained channel. Specifically, in our setup, an agent interacting with an environment transmits encoded estimates of an unknown model parameter to a server over a communication channel of finite capacity. The goal of the server is to take actions based on these estimates to minimize cumulative regret. To this end, we develop a novel and general algorithmic framework that hinges on two main components: (i) an adaptive encoding mechanism that exploits statistical concentration bounds, and (ii) a decision-making principle based on confidence sets that account for encoding errors. As our main result, we prove that when the unknown model is d-dimensional, a channel capacity of O(d) bits suffices to achieve order-optimal regret. We also establish that for the simpler unstructured multi-armed bandit problem, 1 bit channel capacity is sufficient for achieving optimal regret bounds. Keywords: Linear Bandits, Distributed Learning, Communication Constraintsmore » « less
- Free Publicly Accessible Full Text
-
Accepted Manuscript1.0
- Conference Paper:
- https://doi.org/10.1137/1.9781611977912.18
