3 papers
cs.LG2026
LASER: Latent Space Adjoint Matching for Support-Constrained Entropy-Regularized Offline RL
Songyuan Zhang, Oswin So, Eric Yang Yu +3
While offline reinforcement learning (RL) enables policy optimization from static datasets without costly online interaction, it remains bottlenecked by the risk of executing out-o…
cs.LG2026
Solving Parameter-Robust Avoid Problems with Unknown Feasibility using Reinforcement Learning
Oswin So, Eric Yang Yu, Songyuan Zhang +3
Recent advances in deep reinforcement learning (RL) have achieved strong results on high-dimensional control tasks, but applying RL to reachability problems raises a fundamental mi…
cs.LG2026
ReFORM: Reflected Flows for On-support Offline RL via Noise Manipulation
Songyuan Zhang, Oswin So, H. M. Sabbir Ahmad +4
Offline reinforcement learning (RL) aims to learn the optimal policy from a fixed dataset generated by behavior policies without additional environment interactions. One common cha…