Related papers: Learning in Games with Quantized Payoff Observatio…

We investigate the problem of learning an equilibrium in a generalized two-sided matching market, where agents can adaptively choose their actions based on their assigned matches. Specifically, we consider a setting in which matched agents…

In performative learning, the data distribution reacts to the deployed model - for example, because strategic users adapt their features to game it - which creates a more complex dynamic than in classical supervised learning. One should…

When applying reinforcement learning from human feedback (RLHF), the reward is learned from data and, therefore, always has some error. It is common to mitigate this by regularizing the policy with KL divergence from a base model, with the…

Quantization is essential for deploying large language models (LLMs) on resource-constrained hardware, but its implications for multilingual tasks remain underexplored. We conduct the first large-scale evaluation of post-training…

While multi-agent reinforcement learning (MARL) has produced numerous algorithms that converge to Nash or related equilibria, such equilibria are often non-unique and can exhibit widely varying efficiency. This raises a fundamental…

This paper introduces an innovative error feedback framework designed to mitigate quantization noise in distributed graph filtering, where communications are constrained to quantized messages. It comes from error spectrum shaping techniques…

In this paper, we study the problem of learning in quantum games - and other classes of semidefinite games - with scalar, payoff-based feedback. For concreteness, we focus on the widely used matrix multiplicative weights (MMW) algorithm…

In this article we evaluate the statistical evidence that a population of students learn about the sub-game perfect Nash equilibrium of the centipede game via repeated play of the game. This is done by formulating a model in which a…

Long-tail imbalance is endemic to multi-label learning: a few head labels dominate the gradient signal, while the many rare labels that matter in practice are silently ignored. We tackle this problem by casting the task as a cooperative…

Offline multi-agent reinforcement learning is challenging due to the coupling effect of both distribution shift issue common in offline setting and the high dimension issue common in multi-agent setting, making the action…

Quantum federated learning (QFL) merges the privacy advantages of federated systems with the computational potential of quantum neural networks (QNNs), yet its vulnerability to adversarial attacks remains poorly understood. This work…

Reinforcement Learning (RL) is a learning paradigm concerned with learning to control a system so as to maximize an objective over the long term. This approach to learning has received immense interest in recent times and success manifests…

Reinforcement Learning (RL) algorithms have led to recent successes in solving complex games, such as Atari or Starcraft, and to a huge impact in real-world applications, such as cybersecurity or autonomous driving. In the side of the…

Centralized value learning is often assumed to improve coordination and stability in multi-agent reinforcement learning, yet this assumption is rarely tested under controlled conditions. We directly evaluate it in a fully tabular…

Machine learning with artificial neural networks is revolutionizing science. The most advanced challenges require discovering answers autonomously. This is the domain of reinforcement learning, where control strategies are improved…

The application of quantum reinforcement learning (QRL) to real-time control systems faces significant challenges regarding hardware latency, noise susceptibility, and learning convergence. This work presents an end-to-end investigation of…

Game-theoretic approaches and Nash equilibrium have been widely applied across various engineering domains. However, practical challenges such as disturbances, delays, and actuator limitations can hinder the precise execution of Nash…

Generalization poses a significant challenge in Multi-agent Reinforcement Learning (MARL). The extent to which an agent is influenced by unseen co-players depends on the agent's policy and the specific scenario. A quantitative examination…

A commonly used heuristic in RL is experience replay (e.g.~\citet{lin1993reinforcement, mnih2015human}), in which a learner stores and re-uses past trajectories as if they were sampled online. In this work, we initiate a rigorous study of…

We study the problem of no-regret learning algorithms for general monotone and smooth games and their last-iterate convergence properties. Specifically, we investigate the problem under bandit feedback and strongly uncoupled dynamics, which…