This paper introduces mean field reinforcement learning through Markov decision processes in large-population stochastic control, developing the necessary framework for representative-agent learning,…

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…

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 provides a mathematical framework for studying different policy learning problems and shows reductions between them.

A novel multi-agent reinforcement learning algorithm, TC-GQN, is proposed for high-level control and orchestration of mobile networks, enabling energy savings while maintaining QoS.

This paper provides non-asytotic sample complexity guarantees for the Navigate and Stop algorithm in online tabular Reinforcement Learning, identifying additional attributes that affect the overall sa…

SPADER is a novel reinforcement learning framework that addresses the challenges of Multi-Answer Question Answering by improving credit assignment and promoting diverse exploration during long-horizon…

DriftQL introduces a novel, efficient offline RL method that combines a drift-based behavioral regularizer with critic-driven policy improvement, achieving state-of-the-art performance while maintaini…

This paper develops a policy-learning framework to optimally assign prediction tasks to multiple agents, considering individual agent expertise and capacity constraints, achieving systematic performan…

The paper proposes a Hierarchical Reinforcement Learning framework with two levels for handling high-level strategic planning and low-level continuous-control using Soft Actor-Critic and entropy-regul…

This paper introduces Repeated Policy Regret (RP-Regret), a novel game-theoretic metric for analyzing regret in repeated games with adaptive opponents, and proposes algorithms to minimize it.

The paper develops an optimistic maximum-likelihood algorithm that achieves $ ilde{O}(\sqrt{T})$ policy regret for sequential decision-making in partially observable Markov games against adaptive oppo…

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…

QUBRIC introduces a co-design framework that simultaneously optimizes queries and rubrics, overcoming the bottleneck of vague rubrics derived from open-ended questions, leading to significant gains in…

The paper proposes DIBS, a decoupled behavioral cloning approach that stabilizes inductive generalization in RL by separating task-specific policy learning from the evolution function, leading to impr…

The paper proposes a feasible-reward-set framework to perform Inverse Reinforcement Learning (IRL) when data comes from multiple imperfect demonstrators, providing theoretical guarantees and practical…

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…

This paper proposes using Answer-Set Programming (ASP) to implement and evaluate CARCASS abstractions, demonstrating a promising method for constructing powerful abstractions for Reinforcement Learnin…