Search arXiv⌕ Search
Home/Archive/arXiv

arXiv · 2210.13396

Offline congestion games: How feedback type affects data coverage requirement

Haozhe Jiang·Qiwen Cui·Zhihan Xiong·Maryam Fazel·Simon S. Du
View original source ↗Read source document ↗Export metadata ↓

Abstract

This paper investigates when one can efficiently recover an approximate Nash Equilibrium (NE) in offline congestion games. The existing dataset coverage assumption in offline general-sum games inevitably incurs a dependency on the number of actions, which can be exponentially large in congestion games. We consider three different types of feedback with decreasing revealed information. Starting from the facility-level (a.k.a., semi-bandit) feedback, we propose a novel one-unit deviation coverage condition and give a pessimism-type algorithm that can recover an approximate NE. For the agent-level (a.k.a., bandit) feedback setting, interestingly, we show the one-unit deviation coverage condition is not sufficient. On the other hand, we convert the game to multi-agent linear bandits and show that with a generalized data coverage assumption in offline linear bandits, we can efficiently recover the approximate NE. Lastly, we consider a novel type of feedback, the game-level feedback where only the total reward from all agents is revealed. Again, we show the coverage assumption for the agent-level feedback setting is insufficient in the game-level feedback setting, and with a stronger version of the data coverage assumption for linear bandits, we can recover an approximate NE. Together, our results constitute the first study of offline congestion games and imply formal separations between different types of feedback.

Explore related subjects

cs.GTcs.LGcs.MA

Keep this discovery

Explore connections, maps & timelines

BibTeXRIS

Haozhe Jiang, Qiwen Cui, Zhihan Xiong, Maryam Fazel, Simon S. Du. 2024-10-04. Offline congestion games: How feedback type affects data coverage requirement. https://arxiv.org/abs/2210.13396

Cite the original work for its findings. Save a collection to share your selection of sources.

KEEP EXPLORING

Related papers

arXiv2026

Control and Bribery in Stable Marriage and Stable Roommates: A Complete Complexity Landscape

We study control and bribery problems for stable matchings: A central authority (the controller, resp. briber) may add agents, delete agents, delete acceptable pairs, swap two adjacent agents in some agent's preference list, or arbitrarily reorder some agent's preference list, in an instance of Stable Marriage or Stable Roommates. We extend previous work on control and bribery in stable matchings by Boehmer et al. [8]. We consider goals capturing individual and pair inclusion, stability, and uniqueness requirements: Matching a designated agent (MA), matching a designated pair (MP), realizing a stable matching consistent with a given matching (MS), making a given matching the unique stable matching (USM), or guaranteeing that a stable (resp. perfect and stable) matching exists ($\exists$SM/$\exists$PSM). We provide a unified complexity map for all non-trivial action-goal combinations in both settings, consolidating known results and extending the study to the roommates model, where stable matchings need not exist.

cs.GT↗
arXiv2026

How a Cooperative-Override Circuit Suppresses Nash Play in Large Language Models

On the named Prisoner's Dilemma under direct prompting, three larger instruction-tuned models, Llama-3-70B, Qwen2.5-32B, and Qwen2.5-72B, lock at full cooperation, the metric's maximum distance from Nash with zero variance across replicates, while Llama-3-8B plays near-Nash. Opening the models, a logit-lens analysis finds a distributed cooperative override. Intermediate readouts lean toward the Nash action through roughly three quarters of network depth before a late surge toward cooperation, and the final layer settles the contest. The size of that final correction, not the surge, rank-matches chain-of-thought behavior across scale and two architectures. In the 8B the override is a single causally controllable direction in the residual stream; steering it dials the decision, and clamping its component at one position of one layer moves the choice strictly monotonically, Spearman rho = 1.000, with generation fluent. The circuit is lexical. It survives name removal and payoff rescaling but disengages when Cooperate and Defect are replaced with neutral labels, and on 48 payoff-random games with neutral surfaces no model locks cooperative on any dilemma or shows general equilibrium competence. In mixed-model populations a single Nash-playing agent collapses cooperation contagiously. What suppresses Nash play in large language models is a word-triggered circuit rather than missing competence, and it can be measured, bounded, and controlled.

cs.GT↗
arXiv2026

Auction Design with ROI-Constrained Bidders: Truthfulness and Revenue Maximization

The return-on-investment (ROI) constraint is central to many auctions, particularly in online advertising, where a bidder is unwilling to pay more than a fixed fraction of the value obtained. We study truthful and revenue-maximizing auctions for ROI-constrained bidders. We first characterize truthful auctions when both valuations and ROI constraints are private, showing that the allocation rule uniquely determines the payment rule. Building on this characterization, for multiple bidders we introduce $σ$-increment mechanisms that resemble Myerson's optimal mechanism~\cite{journals/mor/Myerson81}; as $σ$ vanishes, these mechanisms become asymptotically optimal among deterministic truthful mechanisms, and their revenue approaches at least a $1/\bar r$ fraction of the optimal expected revenue over all truthful mechanisms, where $\bar r$ is the largest possible ROI constraint. In the single-bidder setting, we prove that every truthful auction can be replaced by a convex pricing function with weakly higher payments for every type, and we derive the optimal pricing functions when either the valuation or the ROI constraint is public.

cs.GT↗