Groot: Learning to follow instructions by watching gameplay videos
We study the problem of building a controller that can follow open-ended instructions in
open-world environments. We propose to follow reference videos as instructions, which offer …
open-world environments. We propose to follow reference videos as instructions, which offer …
Deep generative models for offline policy learning: Tutorial, survey, and perspectives on future directions
Deep generative models (DGMs) have demonstrated great success across various domains,
particularly in generating texts, images, and videos using models trained from offline data …
particularly in generating texts, images, and videos using models trained from offline data …
Multi-task hierarchical adversarial inverse reinforcement learning
Abstract Multi-task Imitation Learning (MIL) aims to train a policy capable of performing a
distribution of tasks based on multi-task expert demonstrations, which is essential for …
distribution of tasks based on multi-task expert demonstrations, which is essential for …
Hierarchical adversarial inverse reinforcement learning
J Chen, T Lan, V Aggarwal - IEEE Transactions on Neural …, 2023 - ieeexplore.ieee.org
Imitation learning (IL) has been proposed to recover the expert policy from demonstrations.
However, it would be difficult to learn a single monolithic policy for highly complex long …
However, it would be difficult to learn a single monolithic policy for highly complex long …
Hierarchical imitation learning with vector quantized models
The ability to plan actions on multiple levels of abstraction enables intelligent agents to solve
complex tasks effectively. However, learning the models for both low and high-level …
complex tasks effectively. However, learning the models for both low and high-level …
Option-aware adversarial inverse reinforcement learning for robotic control
J Chen, T Lan, V Aggarwal - 2023 IEEE International …, 2023 - ieeexplore.ieee.org
Hierarchical Imitation Learning (HIL) has been proposed to recover highly-complex
behaviors in long-horizon tasks from expert demonstrations by modeling the task hierarchy …
behaviors in long-horizon tasks from expert demonstrations by modeling the task hierarchy …
Automated task-time interventions to improve teamwork using imitation learning
Effective human-human and human-autonomy teamwork is critical but often challenging to
perfect. The challenge is particularly relevant in time-critical domains, such as healthcare …
perfect. The challenge is particularly relevant in time-critical domains, such as healthcare …
Shail: Safety-aware hierarchical adversarial imitation learning for autonomous driving in urban environments
Designing a safe and human-like decision-making system for an autonomous vehicle is a
challenging task. Generative imitation learning is one possible approach for automating …
challenging task. Generative imitation learning is one possible approach for automating …
GO-DICE: Goal-Conditioned Option-Aware Offline Imitation Learning via Stationary Distribution Correction Estimation
A Jain, V Unhelkar - Proceedings of the AAAI conference on artificial …, 2024 - ojs.aaai.org
Offline imitation learning (IL) refers to learning expert behavior solely from demonstrations,
without any additional interaction with the environment. Despite significant advances in …
without any additional interaction with the environment. Despite significant advances in …
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 …