A Hypothesis on Black Swan in Unchanging Environments

no code implementations • 25 Jul 2024 • Hyunin Lee, Chanwoo Park, David Abel, Ming Jin

Black swan events are statistically rare occurrences that carry extremely high risks.

Initial State Interventions for Deconfounded Imitation Learning

no code implementations • 29 Jul 2023 • Samuel Pfrommer, Yatong Bai, Hyunin Lee, Somayeh Sojoudi

Imitation learning suffers from causal confusion.

Imitation Learning

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

1 code implementation • 22 May 2022 • Donghao Ying, Mengzi Amy Guo, Hyunin Lee, Yuhao Ding, Javad Lavaei, Zuo-Jun Max Shen

In the exact setting, we prove an $O(T^{-1/3})$ convergence rate for both the average optimality gap and constraint violation, which further improves to $O(T^{-1/2})$ under strong concavity of the objective in the occupancy measure.

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

no code implementations • 19 Oct 2021 • Yuhao Ding, Junzi Zhang, Hyunin Lee, Javad Lavaei

Our result is the first global convergence and sample complexity results for the stochastic entropy-regularized vanilla PG method.

Policy Gradient Methods Reinforcement Learning (RL)