The paper investigates when intrinsic rewards effectively drive exploration in reinforcement learning. It introduces a formal criterion that evaluates policies based on the counterfactual information they acquire, comparing how well their histories can replace experience from alternative policies. Using a simple environment, the authors show that common intrinsic reward objectives—count-based, prediction-error, empowerment, and information-gain—can lead to Pareto-suboptimal exploration under this criterion, and they propose conditions and a new objective that better align with optimal exploration.
By Scott W. Viteri (Stanford University), Laura Gomezjurado Gonzalez (Stanford University), Clark Barrett (Stanford University)
arXiv:2606. 08369v1 Announce Type: cross Abstract: A growing body of work points to the great promise of AI systems that can continually expand their capabilities as they operate in an open-ended environment.
By Wanqiao Xu, Yifan Zhu, Benjamin Van Roy
arXiv:2608. 10529v1 Announce Type: cross Abstract: The multi-armed bandit problem is a central framework in sequential decision-making, extensively studied under sub-Gaussian reward assumptions.
By Daphne Feng, Ricardo Parada, Lily Jiang, Sophia Yi, William Chang
arXiv:2602. 12963v2 Announce Type: replace Abstract: An important question in the field of AI is the extent to which successful behaviour requires an internal representation of the world.
By Alfred Harwood, Jose Faustino, Alex Altair
arXiv:2607. 29419v1 Announce Type: cross Abstract: In reinforcement learning, exploration with sparse and delayed rewards presents a significant challenge due to the limited feedback available for guiding the learning process.
By Bumgeun Park, Donghwan Lee
The paper investigates when information sharing enhances decentralized discovery by separating its effects on pooled estimation and independent rescue actions in finite discovery models. It shows that a registered incremental-sharing protocol improves discovery only when pooled residual error decreases faster than an independent rescue attempt, and that equilibrium selection can determine whether sharing is beneficial. The study uses synthetic, finite models without human or organizational data.
By Yohei Nakajima
arXiv:2609.13564v1 Announce Type: new
Abstract: We study KL-regularized contextual bandits under both reward and preference feedback. We show that greedy sampling can achieve logarithmic regret witho...
By Zichen Wang, Haoyang Hong, Huazheng Wang
The paper introduces Latent Order Bandits (LOB), a new bandit framework that relaxes the strict assumptions of traditional latent bandits by only requiring a partial order of action preferences within each latent state. LOB allows instances sharing the same state to have different reward distributions as long as the action ranking remains consistent, making it suitable for scenarios like user groups on streaming services who agree on genre preferences but rate differently. The authors present an upper‑confidence bound algorithm for both total and partial latent orders, provide regret bounds, and propose a posterior‑sampling variant that empirically outperforms full‑prior latent bandits when reward scales vary across instances sharing the same latent state.
By Emil Carlsson, Newton Mwai, Fredrik D. Johansson
arXiv:2608. 16707v1 Announce Type: cross Abstract: Large language models (LLMs) are increasingly deployed as decision-making agents in settings that require sophisticated environmental exploration.
By David Eric Austin, Kaheer Suleman, Jackie Chi Kit Cheung
The paper investigates preference-based bandits where a learner selects pairs of arms and receives binary preference feedback modeled by Bradley–Terry. It introduces the locally sensitive eluder dimension, a new complexity measure for logistic preference feedback, and proposes the GINOP algorithm that uses log-loss confidence sets to balance optimism and exploration. The authors prove a first-order regret bound showing that learning with preference feedback can be as statistically efficient as learning from direct rewards, and they validate their theory with empirical experiments.
By Ahmed Ben Yahmed (CREST, ENSAE Paris, FAIRPLAY), Marc Abeille (FAIRPLAY), Cl\'ement Calauz\`enes (FAIRPLAY)
arXiv:2505. 08630v2 Announce Type: replace Abstract: Training cooperative agents in sparse-reward scenarios poses significant challenges for multi-agent reinforcement learning (MARL).
By Shuai Han, Mehdi Dastani, Shihan Wang
arXiv:2608. 10526v1 Announce Type: cross Abstract: Motivated by decentralized applications, we study cooperative multi-agent bandits in continuous (Lipschitz) action spaces when the Lipschitz constant is unknown.
By Ricardo Parada, Chenzhang Zhao, William Chang