Towards continual reinforcement learning: A review and perspectives

K Khetarpal, M Riemer, I Rish, D Precup - Journal of Artificial Intelligence …, 2022 - jair.org
In this article, we aim to provide a literature review of different formulations and approaches
to continual reinforcement learning (RL), also known as lifelong or non-stationary RL. We …

Text2motion: From natural language instructions to feasible plans

K Lin, C Agia, T Migimatsu, M Pavone, J Bohg - Autonomous Robots, 2023 - Springer
Abstract We propose Text2Motion, a language-based planning framework enabling robots
to solve sequential manipulation tasks that require long-horizon reasoning. Given a natural …

Learning neuro-symbolic skills for bilevel planning

T Silver, A Athalye, JB Tenenbaum… - arxiv preprint arxiv …, 2022 - arxiv.org
Decision-making is challenging in robotics environments with continuous object-centric
states, continuous actions, long horizons, and sparse feedback. Hierarchical approaches …

Embodied lifelong learning for task and motion planning

J Mendez-Mendez, LP Kaelbling… - … on Robot Learning, 2023 - proceedings.mlr.press
A robot deployed in a home over long stretches of time faces a true lifelong learning
problem. As it seeks to provide assistance to its users, the robot should leverage any …

Predicate invention for bilevel planning

T Silver, R Chitnis, N Kumar, W McClinton… - Proceedings of the …, 2023 - ojs.aaai.org
Efficient planning in continuous state and action spaces is fundamentally hard, even when
the transition model is deterministic and known. One way to alleviate this challenge is to …

Learning efficient abstract planning models that choose what to predict

N Kumar, W McClinton, R Chitnis… - … on Robot Learning, 2023 - proceedings.mlr.press
An effective approach to solving long-horizon tasks in robotics domains with continuous
state and action spaces is bilevel planning, wherein a high-level search over an abstraction …

[PDF][PDF] Inventing relational state and action abstractions for effective and efficient bilevel planning

T Silver, R Chitnis, N Kumar, W McClinton… - arxiv preprint arxiv …, 2022 - aair-lab.github.io
Effective and efficient planning in continuous state and action spaces is fundamentally hard,
even when the transition model is deterministic and known. One way to alleviate this …

Emerging Trends in Machine Learning assisted Optimization Techniques Across Intelligent Transportation Systems

BI Afolayan, A Ghosh, JF Calderin… - IEEE Access, 2024 - ieeexplore.ieee.org
Artificial intelligence (AI) plays a critical role in Intelligent Transport Systems (ITS) as urban
areas grow by processing data for safety enhancements, predictive analysis, and traffic …

Relational decomposition for program synthesis

C Hocquette, A Cropper - arxiv preprint arxiv:2408.12212, 2024 - arxiv.org
We introduce a novel approach to program synthesis that decomposes complex functional
tasks into simpler relational synthesis sub-tasks. We demonstrate the effectiveness of our …

Predicate Invention from Pixels via Pretrained Vision-Language Models

A Athalye, N Kumar, T Silver, Y Liang… - arxiv preprint arxiv …, 2024 - arxiv.org
Our aim is to learn to solve long-horizon decision-making problems in highly-variable,
combinatorially-complex robotics domains given raw sensor input in the form of images …