7 accepted papers
Low-Rank Adaptation (LoRA) is a widely used parameter-efficient fine-tuning technique, and previous works have studied the update dynamics of LoRA, showing that updating via the low-rank matrix $\mathbf{A}$ can be viewed as a process within the compressed subspace defined by $\mathbf{A}^{\top} \math…
In this paper, we study the finite-sample statistical rates of distributional temporal difference (TD) learning with linear function approximation. The aim of distributional TD learning is to estimate the return distribution of a discounted Markov decision process for a given policy $\pi$. Previous…
Automatic colorization techniques often struggle with dual-character line art, particularly in areas such as color coordination between characters, handling complex scenes and interactions, and meeting personalized colorization requirements. To address these challenges, we introduce DuCol, a novel f…
Prompt learning is a common strategy for adapting Visual Language Models (VLMs) to downstream tasks by fine-tuning prompts for task-specific performance. However, existing methods face two key challenges: overfitting to base classes, which limits generalization to novel classes, and the dependence o…
Distributional reinforcement learning (DRL) has achieved empirical success in various domains. One of the core tasks in the field of DRL is distributional policy evaluation, which involves estimating the return distribution $\eta^\pi$ for a given policy $\pi$. The distributional temporal difference…
We study Federated Reinforcement Learning (FedRL) problem in which $n$ agents collaboratively learn a single policy without sharing the trajectories they collected during agent-environment interaction. In this paper, we stress the constraint of environment heterogeneity, which means $n$ environments…
We propose a generalization of constrained Markov decision processes (CMDPs) that we call the \emph{semi-infinitely constrained Markov decision process} (SICMDP). Particularly, in a SICMDP model, we impose a continuum of constraints instead of a finite number of constraints as in the case of ordinar…