activity
20122024
most citedDelta-Complete Decision Procedures for Satisfiability over the Reals

43 citations · 81 across the 16 of their papers we have counts for

collaborators
Showing cs.LGShow all

7 papers · 1 filter

cs.LG2025

When Maximum Entropy Misleads Policy Optimization

Ruipeng Zhang, Ya-Chien Chang, Sicun Gao

The Maximum Entropy Reinforcement Learning (MaxEnt RL) framework is a leading approach for achieving efficient learning and robust performance across many RL tasks. However, MaxEnt…

cs.LG2025

Improving Value Estimation Critically Enhances Vanilla Policy Gradient

Tao Wang, Ruipeng Zhang, Sicun Gao

Modern policy gradient algorithms, such as TRPO and PPO, outperform vanilla policy gradient in many RL tasks. Questioning the common belief that enforcing approximate trust regions…

cs.LG2025

Improving Compositional Generation with Diffusion Models Using Lift Scores

Chenning Yu, Sicun Gao

We introduce a novel resampling criterion using lift scores, for improving compositional generation in diffusion models. By leveraging the lift scores, we evaluate whether generate…

cs.LG2024

Breaking the Barrier: Enhanced Utility and Robustness in Smoothed DRL Agents

Chung-En Sun, Sicun Gao, Tsui-Wei Weng

Robustness remains a paramount concern in deep reinforcement learning (DRL), with randomized smoothing emerging as a key technique for enhancing this attribute. However, a notable…

cs.LG20241 cited

Understanding the Difficulty of Solving Cauchy Problems with PINNs

Tao Wang, Bo Zhao, Sicun Gao +1

Physics-Informed Neural Networks (PINNs) have gained popularity in scientific computing in recent years. However, they often fail to achieve the same level of accuracy as classical…

cs.LG2024

Extremum-Seeking Action Selection for Accelerating Policy Optimization

Ya-Chien Chang, Sicun Gao

Reinforcement learning for control over continuous spaces typically uses high-entropy stochastic policies, such as Gaussian distributions, for local exploration and estimating poli…