Search Results - "Lee, Hyunin"

Explainable Deep Learning Model for EMG-Based Finger Angle Estimation Using Attention by Lee, Hyunin, Kim, Dongwook, Park, Yong-Lae

“…Electromyography (EMG) is one of the most common methods to detect muscle activities and intentions. However, it has been difficult to estimate accurate hand…”
Get full text

A Hypothesis on Black Swan in Unchanging Environments by Lee, Hyunin, Park, Chanwoo, Abel, David, Jin, Ming

“…Black swan events are statistically rare occurrences that carry extremely high risks. A typical view of defining black swan events is heavily assumed to…”
Get full text

Pausing Policy Learning in Non-stationary Reinforcement Learning by Lee, Hyunin, Jin, Ming, Lavaei, Javad, Sojoudi, Somayeh

“…Real-time inference is a challenge of real-world reinforcement learning due to temporal differences in time-varying environments: the system collects data from…”
Get full text

Initial State Interventions for Deconfounded Imitation Learning by Pfrommer, Samuel, Bai, Yatong, Lee, Hyunin, Sojoudi, Somayeh

“…Imitation learning suffers from causal confusion. This phenomenon occurs when learned policies attend to features that do not causally influence the expert…”
Get full text

Tempo Adaptation in Non-stationary Reinforcement Learning by Lee, Hyunin, Ding, Yuhao, Lee, Jongmin, Jin, Ming, Lavaei, Javad, Sojoudi, Somayeh

“…We first raise and tackle a ``time synchronization'' issue between the agent and the environment in non-stationary reinforcement learning (RL), a crucial…”
Get full text

Beyond Exact Gradients: Convergence of Stochastic Soft-Max Policy Gradient Methods with Entropy Regularization by Ding, Yuhao, Zhang, Junzi, Lee, Hyunin, Lavaei, Javad

“…Entropy regularization is an efficient technique for encouraging exploration and preventing a premature convergence of (vanilla) policy gradient methods in…”
Get full text

Policy-based Primal-Dual Methods for Concave CMDP with Variance Reduction by Ying, Donghao, Guo, Mengzi Amy, Lee, Hyunin, Ding, Yuhao, Lavaei, Javad, Shen, Zuo-Jun Max

“…We study Concave Constrained Markov Decision Processes (Concave CMDPs) where both the objective and constraints are defined as concave functions of the…”
Get full text