Related papers: Bootstrapping Linear Models for Fast Online Adapta…
An active learning (AL) algorithm seeks to construct an effective classifier with a minimal number of labeled examples in a bootstrapping manner. While standard AL heuristics, such as selecting those points for annotation for which a…
Training LLMs as interactive agents for multi-turn decision-making remains challenging, particularly in long-horizon tasks with sparse and delayed rewards, where agents must execute extended sequences of actions before receiving meaningful…
We propose incorporating human labelers in a model fine-tuning system that provides immediate user feedback. In our framework, human labelers can interactively query model predictions on unlabeled data, choose which data to label, and see…
Learning robust driving policies from large-scale, real-world datasets is a central challenge in autonomous driving, as online data collection is often unsafe and impractical. While Behavioral Cloning (BC) offers a straightforward approach…
Reinforcement learning (RL) has become a pivotal component of large language model (LLM) post-training, and agentic RL extends this paradigm to operate as agents through multi-turn interaction and tool use. Scaling such systems exposes two…
We introduce an offline reinforcement learning (RL) algorithm that explicitly clones a behavior policy to constrain value learning. In offline RL, it is often important to prevent a policy from selecting unobserved actions, since the…
We propose a framework for adaptive data-centric collaborative machine learning among self-interested agents, coordinated by an arbiter. Designed to handle the incremental nature of real-world data, the framework operates in an online…
Accurate statistical inference in logistic regression models remains a critical challenge when the ratio between the number of parameters and sample size is not negligible. This is because approximations based on either classical asymptotic…
We consider model-based reinforcement learning (MBRL) in 2-agent, high-fidelity continuous control problems -- an important domain for robots interacting with other agents in the same workspace. For non-trivial dynamical systems, MBRL…
Enabling robots to learn novel visuomotor skills in a data-efficient manner remains an unsolved problem with myriad challenges. A popular paradigm for tackling this problem is through leveraging large unlabeled datasets that have many…
Discovering successful coordinated behaviors is a central challenge in Multi-Agent Reinforcement Learning (MARL) since it requires exploring a joint action space that grows exponentially with the number of agents. In this paper, we propose…
Imitation learning enables autonomous agents to learn from human examples, without the need for a reward signal. Still, if the provided dataset does not encapsulate the task correctly, or when the task is too complex to be modeled, such…
While Large Language Models (LLM) enable non-experts to specify open-world multi-robot tasks, the generated plans often lack kinematic feasibility and are not efficient, especially in long-horizon scenarios. Formal methods like Linear…
Reinforcement learning (RL) often struggles with reward misalignment, where agents optimize given rewards but fail to exhibit the desired behaviors. This arises when the reward function incentivizes proxy behaviors misaligned with the true…
Cooperative multi-agent reinforcement learning (MARL) approaches tackle the challenge of finding effective multi-agent cooperation strategies for accomplishing individual or shared objectives in multi-agent teams. In real-world scenarios,…
Training agents that can coordinate zero-shot with humans is a key mission in multi-agent reinforcement learning (MARL). Current algorithms focus on training simulated human partner policies which are then used to train a Cooperator agent.…
Human Activity Recognition (HAR) is a core task in pervasive computing systems, where models must operate under strict computational constraints while remaining robust to heterogeneous and evolving deployment conditions. Recent advances…
This work explores adaptations of successful multi-armed bandits policies to the online contextual bandits scenario with binary rewards using binary classification algorithms such as logistic regression as black-box oracles. Some of these…
Model-based offline reinforcement learning (RL) has emerged as a promising approach for recommender systems, enabling effective policy learning by interacting with frozen world models. However, the reward functions in these world models,…
We consider model-based multi-agent reinforcement learning, where the environment transition model is unknown and can only be learned via expensive interactions with the environment. We propose H-MARL (Hallucinated Multi-Agent Reinforcement…