From Novice to Expert: Cost-Aware Bandits for Evolving Worker Performance in Crowdsensing

Mobile crowdsensing (MCS) is a distributed sensing architecture that utilizes existing sensors on mobile units (MUs) to perform sensing tasks. A mobile crowdsensing platform (MCSP) publishes the sensing tasks and the MUs decide whether to participate in exchange for money. The MCS system is dynamic: the task requirements, the MUs' availability, and their available resources change over time. The MUs aim to find an efficient task participation strategy to maximize their income while the MCSP focuses on maximizing the number of completed tasks. As optimal strategies require perfect non-causal information about the MCS system, which is unavailable in realistic scenarios, the main challenge is to find an efficient task participation strategy for the MUs under incomplete information. To this end, a novel fully decentralized federated deep reinforcement learning algorithm, FDRL-PPO, is proposed. FDRL-PPO enables every MU to learn its own task participation strategy based on its experiences, available resources, and preferences, without relying on perfect non-causal information about the MCS system. To replenish their batteries, the MUs rely on energy harvesting. As a result, their available energy varies over time, leading to varying availability and fragmented learning experiences. To mitigate these challenges, the proposed approach leverages federated learning, enabling MUs to collaboratively improve their models without sharing private raw data like their own experiences. By exchanging only learned models, MUs collectively compensate for individual limitations, and find more scalable, robust, and efficient task participation strategies. Comprehensive evaluations on both synthetic and real-world datasets show that FDRL-PPO consistently outperforms benchmark algorithms in terms of task completion ratio, fairness in task completion, energy consumption, and number of conflicting proposals.

The classic multi-armed bandit (MAB) problem tackles the challenge of accruing maximum reward while making decisions under uncertainty. However, in applications, often the goal is to minimize cost subject to a constraint on the minimum permissible reward, an objective captured by multi-armed bandits with cost-subsidy (MAB-CS). Of interest to this paper is the setting where the quality (reward) constraint is specified relative to the unknown best reward and the cost of each arm is known. We characterize the expected sub-optimal samples required by any policy by proving instance-dependent lower bounds that offer new insight into the problem and are a strict generalization of prior bounds. Then, we propose an algorithm called Cost-Ordered Feasibility (COF) that leverages our insight and intelligently combine samples from all arms to gauge the feasibility of a cheap arm. Thereafter, we analyze COF to establish instance-dependent upper bounds on its expected cumulative cost and quality regret, i.e., relative to the cheapest feasible arm. Finally, we empirically validate the merits of COF, comparing it to baselines from the literature through extensive simulation experiments on the MovieLens and Goodreads datasets as well as representative synthetic instances. Not only does our paper develop qualitatively better theoretical regret upper bounds, but COF also convincingly demonstrates improved empirical performance.

We study repeated bidding in multi-unit discriminatory (pay-as-bid) auctions for a single bidder with per-round utility equal to value minus $α$ times payment, where $α\in[0,1]$ is a cost-of-capital parameter. The bidder aims to maximize cumulative utility over $T$ rounds subject to a total budget $B$. The problem is challenging even without budgets: the action space is exponential in $M$, the maximum demand of the bidder and the valuation vector (context) varies over time. Exploiting a decomposition of utility across units, we develop polynomial-time learning algorithms based on shortest paths in a directed acyclic graph, obtaining sublinear regret under both full-information and bandit feedback. In the bandit setting, the regret is independent of the number of contexts due to complete cross-learning: observing the utility of the chosen action under the realized context reveals the utility for the same action under all counterfactual contexts. With budget constraints, when the average normalized per-round budget $ρ=\frac{B}{MT}<1$, we design a coupled primal-dual algorithm in which the DAG-based procedure uses dual-adjusted edge weights for primal updates, while online gradient descent updates the dual variable, yielding $ρ$-approximate sublinear regret. Finally, we give implementations whose per-round time and space are independent of the number of contexts, enabling scalability to large or even infinite context spaces.