Hyunin Lee

Cross-attention Secretly Performs Orthogonal Alignment in Recommendation Models

Hyunin Lee, Yong Zhang, Hoang Vu Nguyen, Xiaoyi Liu et autres

Cross-domain sequential recommendation (CDSR) aims to align heterogeneous user behavior sequences collected from different domains. While cross-attention is widely used to enhance alignment and improve recommendation performance, its underlying mechanism is not fully understood. Most researchers interpret cross-attention as residual alignment, where …

Policy-based Primal-Dual Methods for Concave CMDP with Variance Reduction

Donghao Ying, Mengzi Amy Guo, Hyunin Lee, Yuhao Ding et autres

We study Concave Constrained Markov Decision Processes (Concave CMDPs) where both the objective and constraints are defined as concave functions of the state-action occupancy measure. We propose the Variance-Reduced Primal-Dual Policy Gradient Algorithm (VR-PDPG), which updates the primal variable via policy gradient …

us, hk (code pays fourni par la source)

Beyond Exact Gradients: Convergence of Stochastic Soft-Max Policy Gradient Methods With Entropy Regularization

Yuhao Ding, Junzi Zhang, Hyunin Lee, Javad Lavaei

Entropy regularization is an efficient technique for encouraging exploration and preventing a premature convergence of (vanilla) policy gradient (PG) methods in reinforcement learning (RL). However, the theoretical understanding of entropy-regularized RL algorithms has been limited. In this article, we revisit the classical …

us (code pays fourni par la source)

A Black Swan Hypothesis: The Role of Human Irrationality in AI Safety

Hyunin Lee, David Lynn Abel, Ming Jin

Black swan events are statistically rare occurrences that carry extremely high risks. A typical view of defining black swan events is heavily assumed to originate from an unpredictable time-varying environments; however, the community lacks a comprehensive definition of black swan events. To …

Pausing Policy Learning in Non-stationary Reinforcement Learning

Hyunin Lee, Ming Jin, Javad Lavaei, Somayeh Sojoudi

Real-time inference is a challenge of real-world reinforcement learning due to temporal differences in time-varying environments: the system collects data from the past, updates the decision model in the present, and deploys it in the future. We tackle a common belief that …

Initial State Interventions for Deconfounded Imitation Learning

Samuel Pfrommer, Yatong Bai, Hyunin Lee, Somayeh Sojoudi

Imitation learning suffers from causal confusion. This phenomenon occurs when learned policies attend to features that do not causally influence the expert actions but are instead spuriously correlated. Causally confused agents produce low open-loop supervised loss but poor closed-loop performance upon deployment. …

us (code pays fourni par la source)

Tempo Adaptation in Non-stationary Reinforcement Learning

Hyunin Lee, Yuhao Ding, Jongmin Lee, Ming Jin et autres

We first raise and tackle a ``time synchronization'' issue between the agent and the environment in non-stationary reinforcement learning (RL), a crucial factor hindering its real-world applications. In reality, environmental changes occur over wall-clock time ($t$) rather than episode progress ($k$), where …

Initial State Interventions for Deconfounded Imitation Learning

Samuel Pfrommer, Yatong Bai, Hyunin Lee, Somayeh Sojoudi

Imitation learning suffers from causal confusion. This phenomenon occurs when learned policies attend to features that do not causally influence the expert actions but are instead spuriously correlated. Causally confused agents produce low open-loop supervised loss but poor closed-loop performance upon deployment. …

Explainable Deep Learning Model for EMG-Based Finger Angle Estimation Using Attention

Hyunin Lee, DongWook Kim, Yong‐Lae Park

Electromyography (EMG) is one of the most common methods to detect muscle activities and intentions. However, it has been difficult to estimate accurate hand motions represented by the finger joint angles using EMG signals. We propose an encoder-decoder network with an attention …

kr (code pays fourni par la source)