IDIL: Imitation Learning of Intent-Driven Expert Behavior
S Seo, V Unhelkar - arXiv preprint arXiv:2404.16989, 2024 - arxiv.org
When faced with accomplishing a task, human experts exhibit intentional behavior. Their
unique intents shape their plans and decisions, resulting in experts demonstrating diverse …
unique intents shape their plans and decisions, resulting in experts demonstrating diverse …
Online Inverse Reinforcement Learning with Learned Observation Model
With the motivation of extending incremental inverse reinforcement learning (I2RL) to real-
world robotics applications with noisy observations as well as an unknown observation …
world robotics applications with noisy observations as well as an unknown observation …
MVSA-Net: Multi-View State-Action Recognition for Robust and Deployable Trajectory Generation
The learn-from-observation (LfO) paradigm is a human-inspired mode for a robot to learn to
perform a task simply by watching it being performed. LfO can facilitate robot integration on …
perform a task simply by watching it being performed. LfO can facilitate robot integration on …
The Principle of Uncertain Maximum Entropy
The principle of maximum entropy, as introduced by Jaynes in information theory, has
contributed to advancements in various domains such as Statistical Mechanics, Machine …
contributed to advancements in various domains such as Statistical Mechanics, Machine …
Notes on Generalizing the Maximum Entropy Principle to Uncertain Data
K Bogert - arXiv preprint arXiv:2109.04530, 2021 - arxiv.org
The principle of maximum entropy is a broadly applicable technique for computing a
distribution with the least amount of information possible constrained to match empirical …
distribution with the least amount of information possible constrained to match empirical …