Is Conditional Generative Modeling all you need for Decision-Making?

no code implementations • 28 Nov 2022 • Anurag Ajay, Yilun Du, Abhi Gupta, Joshua Tenenbaum, Tommi Jaakkola, Pulkit Agrawal

We further demonstrate the advantages of modeling policies as conditional diffusion models by considering two other conditioning variables: constraints and skills.

Decision Making Offline RL +1

Transfer RL via the Undo Maps Formalism

no code implementations • 26 Nov 2022 • Abhi Gupta, Ted Moskovitz, David Alvarez-Melis, Aldo Pacchiano

Transferring knowledge across domains is one of the most fundamental problems in machine learning, but doing so effectively in the context of reinforcement learning remains largely an open problem.

Imitation Learning Transfer Learning

SQUIRL: Robust and Efficient Learning from Video Demonstration of Long-Horizon Robotic Manipulation Tasks

no code implementations • 10 Mar 2020 • Bohan Wu, Feng Xu, Zhanpeng He, Abhi Gupta, Peter K. Allen

This paper aims to address this scalability challenge with a robust, sample-efficient, and general meta-IRL algorithm, SQUIRL, that performs a new but related long-horizon task robustly given only a single video demonstration.

reinforcement-learning Reinforcement Learning (RL)