Zeyu Feng

Zeyu Feng

3 Posts

Diffusion Meets Options: Hierarchical Generative Skill Composition for Temporally-Extended Tasks

DOPPLER is a new framework that combines diffusion models and hierarchical reinforcement learning to let robots plan and replan complex, long-horizon tasks from offline data with robustness in the real world.

LTLDoG: Satisfying Temporally-Extended Symbolic Constraints for Safe Diffusion-based Planning

We develop a safe planning method for trajectory generation by sampling from diffusion model under different LTLf constraints.

Safety-Constrained Policy Transfer with Successor Features

Transfer source policies to a target reinforcement learning task with safety constraints using Successor Features.