The paper proposes DNQ, a scalable solver-in-the-loop framework for training agents in multi-turn simultaneous bidding games by leveraging pairwise payoff estimation to approximate complex equilibrium…

This paper studies a dynamic assortment problem on a two-sided service platform with incomplete information and heterogeneous customers, and develops a data-driven algorithm to learn parameters and op…

This paper studies a dynamic assortment problem on a two-sided service platform with incomplete information and heterogeneous customers, and develops a data-driven algorithm to learn parameters and op…

The paper introduces the Terminal Representation (TR), a novel, lower-dimensional, and structurally distinct formulation for encoding reward-weighted trajectories in RL that bypasses the need for eige…

The paper addresses the failure of fixed-price inference in resource-constrained pricing controllers by developing a target-aware controller that tracks local densities and provides certified, shrinki…

The paper proposes a novel temporal and structural credit assignment framework to efficiently optimize multi-agent LLM systems by decomposing the error signal and using targeted, discrete gradient upd…

The paper proposes a scalable, distributed approach for constrained Multi-Agent Reinforcement Learning by using local consensus over dual variables to ensure global constraint satisfaction without cen…

The paper introduces a novel paradigm where a fine-tuned LLM acts as an ancillary predictor to forecast likely advertisers, significantly improving ad recommendation systems by augmenting candidate ge…

The paper introduces Global PSRO, a novel deep reinforcement learning framework that efficiently approximates Nash equilibria in large two-player zero-sum games by intelligently expanding the strategy…

This paper analyzes Best-of-$N$ preference data, deriving explicit reward targets for independent-reference variants and establishing design principles for choosing $N$ and the base distribution to op…

AlphaToken is a novel response token valuation framework that improves LLM post-training by decoupling token selection into task-specific adaptation and stability preservation, leading to better perfo…

This paper provides the first non-vacuous generalization analysis for the Stochastic Variance Reduced Gradient (SVRG) method by establishing sharp, data-dependent algorithmic stability bounds, thereby…

The paper proposes DARTS, a distribution-aware active rollout trajectory shaping method that fundamentally accelerates LLM reinforcement learning by actively shaping the long-tail response distributio…

The paper proposes a novel Bayesian framework to learn the optimal decision strategy for the stochastic shortest path problem by directly constructing the posterior beliefs for the action-value functi…

The paper introduces the Markov decision contest, a new framework for reinforcement learning using pairwise preferences, and proves that stationary Markov policies are optimal and solvable efficiently…

This paper shows that standard optimal control in Markov Decision Processes (MDPs) with an absorbing catastrophic state naturally generates behavioral signatures mimicking prospect theory, even withou…

The paper proposes S2L-PO, a framework that uses smaller, naturally diverse models as structured explorers to enhance the policy-level diversity and performance of larger language models during traini…

AlphaTransit introduces a novel search-based planning framework that combines Monte Carlo Tree Search (MCTS) with a neural policy-value network to efficiently design high-quality, city-scale bus trans…

The paper introduces Prompted Policy Optimization (PromptPO), an LLM-based method that successfully optimizes policies for various sequential RL tasks, demonstrating that LLMs can replace classical RL…