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 …

Large sequence models for sequential decision-making: a survey

M Wen, R Lin, H Wang, Y Yang, Y Wen, L Mai… - Frontiers of Computer …, 2023‏ - Springer
Transformer architectures have facilitated the development of large-scale and general-
purpose sequence models for prediction tasks in natural language processing and computer …

A survey of zero-shot generalisation in deep reinforcement learning

R Kirk, A Zhang, E Grefenstette, T Rocktäschel - Journal of Artificial …, 2023‏ - jair.org
The study of zero-shot generalisation (ZSG) in deep Reinforcement Learning (RL) aims to
produce RL algorithms whose policies generalise well to novel unseen situations at …

Diffusion model is an effective planner and data synthesizer for multi-task reinforcement learning

H He, C Bai, K Xu, Z Yang, W Zhang… - Advances in neural …, 2023‏ - proceedings.neurips.cc
Diffusion models have demonstrated highly-expressive generative capabilities in vision and
NLP. Recent studies in reinforcement learning (RL) have shown that diffusion models are …

Gnfactor: Multi-task real robot learning with generalizable neural feature fields

Y Ze, G Yan, YH Wu, A Macaluso… - … on Robot Learning, 2023‏ - proceedings.mlr.press
It is a long-standing problem in robotics to develop agents capable of executing diverse
manipulation tasks from visual observations in unstructured real-world environments. To …

Conflict-averse gradient descent for multi-task learning

B Liu, X Liu, X **, P Stone… - Advances in Neural …, 2021‏ - proceedings.neurips.cc
The goal of multi-task learning is to enable more efficient learning than single task learning
by sharing model structures for a diverse set of tasks. A standard multi-task learning …

Multi-task learning with deep neural networks: A survey

M Crawshaw - arxiv preprint arxiv:2009.09796, 2020‏ - arxiv.org
Multi-task learning (MTL) is a subfield of machine learning in which multiple tasks are
simultaneously learned by a shared model. Such approaches offer advantages like …

Transfer learning in deep reinforcement learning: A survey

Z Zhu, K Lin, AK Jain, J Zhou - IEEE Transactions on Pattern …, 2023‏ - ieeexplore.ieee.org
Reinforcement learning is a learning paradigm for solving sequential decision-making
problems. Recent years have witnessed remarkable progress in reinforcement learning …

Mt-opt: Continuous multi-task robotic reinforcement learning at scale

D Kalashnikov, J Varley, Y Chebotar… - arxiv preprint arxiv …, 2021‏ - arxiv.org
General-purpose robotic systems must master a large repertoire of diverse skills to be useful
in a range of daily tasks. While reinforcement learning provides a powerful framework for …

Multi-task learning as a bargaining game

A Navon, A Shamsian, I Achituve, H Maron… - arxiv preprint arxiv …, 2022‏ - arxiv.org
In Multi-task learning (MTL), a joint model is trained to simultaneously make predictions for
several tasks. Joint training reduces computation costs and improves data efficiency; …