Insights into Pre-training via Simpler Synthetic Tasks

1 code implementation • 21 Jun 2022 • Yuhuai Wu, Felix Li, Percy Liang

Second, to our surprise, we find that pre-training on a simple and generic synthetic task defined by the Set function achieves $65\%$ of the benefits, almost matching LIME.

On-Policy Robot Imitation Learning from a Converging Supervisor

no code implementations • 8 Jul 2019 • Ashwin Balakrishna, Brijen Thananjeyan, Jonathan Lee, Felix Li, Arsh Zahed, Joseph E. Gonzalez, Ken Goldberg

Existing on-policy imitation learning algorithms, such as DAgger, assume access to a fixed supervisor.

Continuous Control Imitation Learning +1

Safety Augmented Value Estimation from Demonstrations (SAVED): Safe Deep Model-Based RL for Sparse Cost Robotic Tasks

no code implementations • 31 May 2019 • Brijen Thananjeyan, Ashwin Balakrishna, Ugo Rosolia, Felix Li, Rowan Mcallister, Joseph E. Gonzalez, Sergey Levine, Francesco Borrelli, Ken Goldberg

Reinforcement learning (RL) for robotics is challenging due to the difficulty in hand-engineering a dense cost function, which can lead to unintended behavior, and dynamical uncertainty, which makes exploration and constraint satisfaction challenging.

Model-based Reinforcement Learning reinforcement-learning +1