In recent years, the development of robotics and artificial intelligence (AI) systems has been
nothing short of remarkable. As these systems continue to evolve, they are being utilized in …

Diffusion models have emerged as powerful generative models in the text-to-image domain.
This paper studies their application as observation-to-action models for imitating human …

Imitation learning (IL), a burgeoning frontier in machine learning, holds immense promise
across diverse domains. In recent years, its integration into robotics has sparked significant …

In many sequential decision-making problems (eg, robotics control, game playing,
sequential prediction), human or expert data is available containing useful information about …

Deep reinforcement learning (RL) has led to many recent and groundbreaking advances.
However, these advances have often come at the cost of both increased scale in the …

Imitation learning holds tremendous promise in learning policies efficiently for complex
decision making problems. Current state-of-the-art algorithms often use inverse …

In this paper, we present ContExtual Imitation Learning (CEIL), a general and broadly
applicable algorithm for imitation learning (IL). Inspired by the formulation of hindsight …

Pre-trained text-to-image generative models can produce diverse, semantically rich, and
realistic images from natural language descriptions. Compared with language, images …

Convex Reinforcement Learning (RL) is a recently introduced framework that generalizes
the standard RL objective to any convex (or concave) function of the state distribution …

We provide a unifying view of a large family of previous imitation learning algorithms through
the lens of moment matching. At its core, our classification scheme is based on whether the …