Zobrazeno 1 - 10
of 47
pro vyhledávání: '"Perrault, Andrew"'
Large Multimodal Models (LMMs) excel at comprehending human instructions and demonstrate remarkable results across a broad spectrum of tasks. Reinforcement Learning from Human Feedback (RLHF) and AI Feedback (RLAIF) further refine LLMs by aligning th
Externí odkaz:
http://arxiv.org/abs/2407.00087
Autor:
Byun, Ju-Seung, Perrault, Andrew
Reinforcement learning (RL) training is inherently unstable due to factors such as moving targets and high gradient variance. Reinforcement Learning from Human Feedback (RLHF) and Reinforcement Learning from AI Feedback (RLAIF) can introduce addition
Externí odkaz:
http://arxiv.org/abs/2405.17618
Recent advancements in generative models have sparked significant interest within the machine learning community. Particularly, diffusion models have demonstrated remarkable capabilities in synthesizing images and speech. Studies such as those by Lee
Externí odkaz:
http://arxiv.org/abs/2405.14632
We study reinforcement learning in the presence of an unknown reward perturbation. Existing methodologies for this problem make strong assumptions including reward smoothness, known perturbations, and/or perturbations that do not modify the optimal p
Externí odkaz:
http://arxiv.org/abs/2401.05710
In recent years, there has been growing interest in developing robust machine learning (ML) models that can withstand adversarial attacks, including one of the most widely adopted, efficient, and interpretable ML algorithms-decision trees (DTs). This
Externí odkaz:
http://arxiv.org/abs/2312.09078
Autor:
Xu, Lily, Rolf, Esther, Beery, Sara, Bennett, Joseph R., Berger-Wolf, Tanya, Birch, Tanya, Bondi-Kelly, Elizabeth, Brashares, Justin, Chapman, Melissa, Corso, Anthony, Davies, Andrew, Garg, Nikhil, Gaylard, Angela, Heilmayr, Robert, Kerner, Hannah, Klemmer, Konstantin, Kumar, Vipin, Mackey, Lester, Monteleoni, Claire, Moorcroft, Paul, Palmer, Jonathan, Perrault, Andrew, Thau, David, Tambe, Milind
In this white paper, we synthesize key points made during presentations and discussions from the AI-Assisted Decision Making for Conservation workshop, hosted by the Center for Research on Computation and Society at Harvard University on October 20-2
Externí odkaz:
http://arxiv.org/abs/2307.08774
Predict-then-Optimize is a framework for using machine learning to perform decision-making under uncertainty. The central research question it asks is, "How can the structure of a decision-making task be used to tailor ML models for that specific tas
Externí odkaz:
http://arxiv.org/abs/2305.16830
Autor:
Byun, Ju-Seung, Perrault, Andrew
Learning a predictive model of the mean return, or value function, plays a critical role in many reinforcement learning algorithms. Distributional reinforcement learning (DRL) has been shown to improve performance by modeling the value distribution,
Externí odkaz:
http://arxiv.org/abs/2208.13125
Decision-Focused Learning (DFL) is a paradigm for tailoring a predictive model to a downstream optimization task that uses its predictions in order to perform better on that specific task. The main technical challenge associated with DFL is that it r
Externí odkaz:
http://arxiv.org/abs/2203.16067
Autor:
Byun, Ju-Seung, Perrault, Andrew
Humans decompose novel complex tasks into simpler ones to exploit previously learned skills. Analogously, hierarchical reinforcement learning seeks to leverage lower-level policies for simple tasks to solve complex ones. However, because each lower-l
Externí odkaz:
http://arxiv.org/abs/2110.04357