相关论文: Recoverability Has a Law: The ERR Measure for Tool…

Reinforcement learning (RL) so far has limited real-world applications. One key challenge is that typical RL algorithms heavily rely on a reset mechanism to sample proper initial states; these reset mechanisms, in practice, are expensive to…

We consider the problem setting of prediction with expert advice with possibly heavy-tailed losses, i.e. the only assumption on the losses is an upper bound on their second moments, denoted by $\theta$. We develop adaptive algorithms that…

Tool-integrated reasoning (TIR) enables LLM agents to solve tasks through planning, tool use, and iterative revision, but outcome-only reinforcement learning in this setting suffers from sparse, delayed rewards and weak step-level credit…

We study a repeated Principal Agent problem between a long lived Principal and Agent pair in a prior free setting. In our setting, the sequence of realized states of nature may be adversarially chosen, the Agent is non-myopic, and the…

We study online learning settings in which experts act strategically to maximize their influence on the learning algorithm's predictions by potentially misreporting their beliefs about a sequence of binary events. Our goal is twofold.…

We consider estimation and control in linear time-varying dynamical systems from the perspective of regret minimization. Unlike most prior work in this area, we focus on the problem of designing causal estimators and controllers which…

Recent advances, such as RegretNet, ALGnet, RegretFormer and CITransNet, use deep learning to approximate optimal multi item auctions by relaxing incentive compatibility (IC) and measuring its violation via ex post regret. However, the true…

Large language models are highly capable of answering difficult questions by retrieving, recombining, and attending to information in long contexts. For agentic tasks, an additional capability is required: the preservation of an exact state…

On-policy imitation learning algorithms such as DAgger evolve a robot control policy by executing it, measuring performance (loss), obtaining corrective feedback from a supervisor, and generating the next policy. As the loss between…

Recent studies have found that model performance has a smooth power-law relationship, or scaling laws, with training data and model size, for a wide range of problems. These scaling laws allow one to choose nearly optimal data and model…

Performance of adaptive control policies is assessed through the regret with respect to the optimal regulator, which reflects the increase in the operating cost due to uncertainty about the dynamics parameters. However, available results in…

Unsupervised skill discovery aims to learn diverse and distinguishable behaviors in open-ended reinforcement learning. For existing methods, they focus on improving diversity through pure exploration, mutual information optimization, and…

Understanding emerging behaviors of reinforcement learning (RL) agents may be difficult since such agents are often trained in complex environments using highly complex decision making procedures. This has given rise to a variety of…

Model Multiplicity (MM) arises when multiple, equally performing machine learning models can be trained to solve the same prediction task. Recent studies show that models obtained under MM may produce inconsistent predictions for the same…

Current LLM agents operate under an implicit but universal assumption: execution is a transaction -- the user submits a request, the agent works in isolation, and only upon completion does the dialogue resume. This forces users into a…

While speech-enabled teachable agents have some advantages over typing-based ones, they are vulnerable to errors stemming from misrecognition by automatic speech recognition (ASR). These errors may propagate, resulting in unexpected changes…

Traditional reinforcement learning usually assumes either episodic interactions with resets or continuous operation to minimize average or cumulative loss. While episodic settings have many theoretical results, resets are often unrealistic…

While Bayesian-based exploration often demonstrates superior empirical performance compared to bonus-based methods in model-based reinforcement learning (RL), its theoretical understanding remains limited for model-free settings. Existing…

Reconstructing numerical simulations from control systems research papers is often hindered by underspecified parameters and ambiguous implementation details. We define the task of Paper to Simulation Recoverability, the ability of an…

In this paper, we study the problem of regret minimization for episodic Reinforcement Learning (RL) both in the model-free and the model-based setting. We focus on learning with general function classes and general model classes, and we…