Related papers: Evaluating Deep Human-in-the-Loop Optimization for…

Deep Reinforcement Learning (DRL) algorithms often require a large amount of data and struggle in sparse-reward domains with long planning horizons and multiple sub-goals. In this paper, we propose a neuro-symbolic extension of Proximal…

Automated hyperparameter optimization (HPO) can support practitioners to obtain peak performance in machine learning models. However, there is often a lack of valuable insights into the effects of different hyperparameters on the final…

The utility of Human-in-the-loop telerobotic systems (HiLTS) is driven in part by the quality of feedback it can provide to the operator. While the dynamic interaction between robot and environment can often be sensed or modeled, the…

Bootstrapping from pre-trained language models has been proven to be an efficient approach for building vision-language models (VLM) for tasks such as image captioning or visual question answering. However, outputs of these models rarely…

We study reinforcement learning in hybrid discrete-continuous action spaces, such as settings where the discrete component selects a regime (or index) and the continuous component optimizes within it -- a structure common in robotics,…

Designers reportedly struggle with design optimization tasks where they are asked to find a combination of design parameters that maximizes a given set of objectives. In HCI, design optimization problems are often exceedingly complex,…

Hip exoskeletons are increasing in popularity due to their effectiveness across various scenarios and their ability to adapt to different users. However, personalizing the assistance often requires lengthy tuning procedures and…

Demonstrations are an effective alternative to task specification for learning agents in settings where designing a reward function is difficult. However, demonstrating expert behavior in the action space of the agent becomes unwieldy when…

Post-training paradigms for Large Language Models (LLMs), primarily Supervised Fine-Tuning (SFT) and Reinforcement Learning (RL), face a fundamental dilemma: SFT provides stability (low variance) but suffers from high fitting bias, while RL…

Inductive Logic Programming (ILP) combines rule-based and statistical artificial intelligence methods, by learning a hypothesis comprising a set of rules given background knowledge and constraints for the search space. We focus on extending…

Vision-language foundation models (VLMs) show promise for diverse imaging tasks but often underperform on medical benchmarks. Prior efforts to improve performance include model finetuning, which requires large domain-specific datasets and…

The development and deployment of systems using supervised machine learning (ML) remain challenging: mainly due to the limited reliability of prediction models and the lack of knowledge on how to effectively integrate human intelligence…

The rapidly increasing capabilities of large language models (LLMs) raise an urgent need to align AI systems with diverse human preferences to simultaneously enhance their usefulness and safety, despite the often conflicting nature of these…

Artificial limbs are sophisticated devices to assist people with tasks of daily living. Despite advanced robotic prostheses demonstrating similar motion capabilities to biological limbs, users report them difficult and non-intuitive to use.…

Learning from demonstrations is a useful way to transfer a skill from one agent to another. While most imitation learning methods aim to mimic an expert skill by following the demonstration step-by-step, imitating every step in the…

Deep Reinforcement Learning (RL) has emerged as a promising method to develop humanoid robot locomotion controllers. Despite the robust and stable locomotion demonstrated by previous RL controllers, their behavior often lacks the natural…

Machine learning methods are progressively gaining acceptance in the electron microscopy community for de-noising, semantic segmentation, and dimensionality reduction of data post-acquisition. The introduction of the APIs by major…

In this work, we present a new deterministic partition-based global optimization algorithm, HALO (Hybrid Adaptive Lipschitzian Optimization), which uses estimates of the local Lipschitz constants associated with different sub-regions of the…

Reinforcement Learning with Human Feedback (RLHF) enhances the alignment of Large Language Models (LLMs). However, its limitations have led to the development of Direct Preference Optimization (DPO), an RL-free approach designed to overcome…

In this paper, we study reinforcement learning (RL) algorithms to solve real-world decision problems with the objective of maximizing the long-term reward as well as satisfying cumulative constraints. We propose a novel first-order policy…