Related papers: RL-ABC: Reinforcement Learning for Accelerator Bea…

We develop a machine-learning framework to learn hyperparameter sequences for accelerated first-order methods (e.g., the step size and momentum sequences in accelerated gradient descent) to quickly solve parametric convex optimization…

Policy gradient methods in actor-critic reinforcement learning (RL) have become perhaps the most promising approaches to solving continuous optimal control problems. However, the trial-and-error nature of RL and the inherent randomness…

Constrained Reinforcement Learning (RL) has emerged as a significant research area within RL, where integrating constraints with rewards is crucial for enhancing safety and performance across diverse control tasks. In the context of heating…

Model-based reinforcement learning (RL) is anticipated to exhibit higher sample efficiency compared to model-free RL by utilizing a virtual environment model. However, it is challenging to obtain sufficiently accurate representations of the…

We provide a framework for incorporating robustness -- to perturbations in the transition dynamics which we refer to as model misspecification -- into continuous control Reinforcement Learning (RL) algorithms. We specifically focus on…

Asynchronous execution is essential for scaling reinforcement learning (RL) to modern large model workloads, including large language models and AI agents, but it can fundamentally alter RL optimization behavior. While prior work on…

With the rise of LLMs, there is an increasing need for intelligent recommendation assistants that can handle complex queries and provide personalized, reasoning-driven recommendations. LLM-based recommenders show potential but face…

Reinforcement learning provides an appealing framework for robotic control due to its ability to learn expressive policies purely through real-world interaction. However, this requires addressing real-world constraints and avoiding…

This paper presents a safe learning-based eco-driving framework tailored for mixed traffic flows, which aims to optimize energy efficiency while guaranteeing safety during real-system operations. Even though reinforcement learning (RL) is…

Due to the demand for efficient fine-tuning of large language models, Low-Rank Adaptation (LoRA) has been widely adopted as one of the most effective parameter-efficient fine-tuning methods. Nevertheless, while LoRA improves efficiency,…

Reinforcement learning (RL) has recently become the core paradigm for aligning and strengthening large language models (LLMs). Yet, applying RL in off-policy settings--where stale data from past policies are used for training--improves…

Quantum control requires high-precision and robust control pulses to ensure optimal system performance. However, control sequences generated with a system model may suffer from model bias, leading to low fidelity. While model-free…

Ensembling large language models (LLMs) can effectively combine diverse strengths of different models, offering a promising approach to enhance performance across various tasks. However, existing methods typically rely on fixed weighting…

Dense image captioning is critical for cross-modal alignment in vision-language pretraining and text-to-image generation, but scaling expert-quality annotations is prohibitively expensive. While synthetic captioning via strong…

Reinforcement learning (RL) is an area of significant research interest, and safe RL in particular is attracting attention due to its ability to handle safety-driven constraints that are crucial for real-world applications. This work…

Determining the optimal cost function parameters of Model Predictive Control (MPC) to optimize multiple control objectives is a challenging and time-consuming task. Multiobjective Bayesian Optimization (BO) techniques solve this problem by…

Recent work increasingly focuses on improving the reasoning capabilities of Multimodal Large Language Models (MLLMs). Among existing methods, Process Reward Models (PRMs) stand out for offering dense, step-wise supervision to guide…

MLLMs have been successfully applied to multimodal embedding tasks, yet their generative reasoning capabilities remain underutilized. Directly incorporating chain-of-thought reasoning into embedding learning introduces two fundamental…

Reinforcement learning (RL), known for its self-evolution capability, offers a promising approach to training high-level autonomous driving systems. However, handling constraints remains a significant challenge for existing RL algorithms,…

A key challenge in lifelong reinforcement learning (RL) is the loss of plasticity, where previous learning progress hinders an agent's adaptation to new tasks. While regularization and resetting can help, they require precise hyperparameter…