Yinlam Chow

Control-Aware Representations for Model-based Reinforcement Learning

2020 · arXiv (Cornell University)

A major challenge in modern reinforcement learning (RL) is efficient control of dynamical systems from high-dimensional sensory observations. Learning controllable embedding (LCE) is a promising approach that addresses this challenge by embedding the observations into …

SAFER: Data-Efficient and Safe Reinforcement Learning via Skill Acquisition

2022 · arXiv (Cornell University)

Methods that extract policy primitives from offline demonstrations using deep generative models have shown promise at accelerating reinforcement learning(RL) for new tasks. Intuitively, these methods should also help to trainsafeRLagents because they enforce useful skills. …