CORTEXA
← Browse
arxivcs.GTcs.LG2026-07-14

On Incentivized Exploration beyond Bayesianism and Full-Information

Dimitar Chakarov, Lee Cohen, Nathan Srebro

We extend Incentive Compatible Exploration beyond the Bayesian full-information setting of Kremer et al. [2014]. We consider agents that may possess external information unknown to the principal. We show such settings require new notions of incentivized exploration, as well as going beyond a Bayesian perspective, and we introduce a definition where agents choose any reasonable (undominated) action. Furthermore, our framework provides for a more robust treatment of ties, and extends to settings where agents lack a single common prior and instead only know that reward distributions belong to a collection of potential priors.

View free PDFSource page

Related papers

arxivcs.GTcs.AIcs.LGcs.MA2026-07-10

Beyond Bayesian Nash: Learning Minimax-Regret Equilibria for Adversarial Team Games under Asymmetric Information

Naman Aggarwal, Jonathan P. How

Adversarial team games (ATGs) with asymmetric information, such as adversarial path-finding, goal search, and reachability games on graphs, require strategies that are robust to hidden opponent types, such as a hidden goal flag, and to deception. Under asymmetric information, dec…

View free PDFSource page
arxivcs.GTcs.AIcs.CRcs.LGcs.MA2026-07-10

A Knowledge-Based Multi-Agent Framework for Security Control Recommendation

Carolina Fernández-Martínez, Shuaib Siddiqui, Vanesa Daza

Hardening IT on-premises environments can be a daunting task for teams without access to adequate cybersecurity expertise. In this regard, Decision Support Systems (DSS) with embedded expert knowledge can assist users by guiding them with security recommendations to meet their ob…

View free PDFSource page
arxivcs.LGcs.GT2026-07-07

Strategic Bargaining in Multi-Buyer Markets: Reinforcement Learning from Verifiable Rewards for LLM Negotiations

Shuze Daniel Liu, Claire Chen, Jiabao Sean Xiao, Xin Chen, David Simchi-Levi

Negotiation is a fundamental strategic interaction in management science, characterized by agents attempting to reach agreements while protecting private information, such as reservation costs and hidden valuations. A prevalent yet complex scenario involves a single seller negoti…

View free PDFSource page
arxivcs.LGcs.GT2026-07-16

PAC Learning in Turn-Based Stochastic Games with Reachability Objectives: A Decentralized Private Approach via Expected Conditional Distance

Ali Asadi, Krishnendu Chatterjee, Pavol Kebis

Reachability is the most fundamental logical objective, yet it is notoriously difficult to learn in reinforcement learning settings: even for Markov decision processes, PAC learning of reachability is impossible without additional assumptions. This difficulty also holds in turn-b…

View free PDFSource page