Domain generalization: A survey

K Zhou, Z Liu, Y Qiao, T **ang… - IEEE transactions on …, 2022‏ - ieeexplore.ieee.org
Generalization to out-of-distribution (OOD) data is a capability natural to humans yet
challenging for machines to reproduce. This is because most learning algorithms strongly …

A review of mobile robot motion planning methods: from classical motion planning workflows to reinforcement learning-based architectures

L Dong, Z He, C Song, C Sun - Journal of Systems Engineering …, 2023‏ - ieeexplore.ieee.org
Motion planning is critical to realize the autonomous operation of mobile robots. As the
complexity and randomness of robot application scenarios increase, the planning capability …

The many faces of robustness: A critical analysis of out-of-distribution generalization

D Hendrycks, S Basart, N Mu… - Proceedings of the …, 2021‏ - openaccess.thecvf.com
We introduce four new real-world distribution shift datasets consisting of changes in image
style, image blurriness, geographic location, camera operation, and more. With our new …

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 …

Reinforcement learning with augmented data

M Laskin, K Lee, A Stooke, L Pinto… - Advances in neural …, 2020‏ - proceedings.neurips.cc
Learning from visual observations is a fundamental yet challenging problem in
Reinforcement Learning (RL). Although algorithmic advances combined with convolutional …

[PDF][PDF] A survey of reinforcement learning from human feedback

T Kaufmann, P Weng, V Bengs… - arxiv preprint arxiv …, 2023‏ - researchgate.net
Reinforcement learning from human feedback (RLHF) is a variant of reinforcement learning
(RL) that learns from human feedback instead of relying on an engineered reward function …

Leveraging procedural generation to benchmark reinforcement learning

K Cobbe, C Hesse, J Hilton… - … conference on machine …, 2020‏ - proceedings.mlr.press
Abstract We introduce Procgen Benchmark, a suite of 16 procedurally generated game-like
environments designed to benchmark both sample efficiency and generalization in …

Stabilizing deep q-learning with convnets and vision transformers under data augmentation

N Hansen, H Su, X Wang - Advances in neural information …, 2021‏ - proceedings.neurips.cc
While agents trained by Reinforcement Learning (RL) can solve increasingly challenging
tasks directly from visual observations, generalizing learned skills to novel environments …

Robust and generalizable visual representation learning via random convolutions

Z Xu, D Liu, J Yang, C Raffel, M Niethammer - arxiv preprint arxiv …, 2020‏ - arxiv.org
While successful for various computer vision tasks, deep neural networks have shown to be
vulnerable to texture style shifts and small perturbations to which humans are robust. In this …

Broaden your views for self-supervised video learning

A Recasens, P Luc, JB Alayrac… - Proceedings of the …, 2021‏ - openaccess.thecvf.com
Most successful self-supervised learning methods are trained to align the representations of
two independent views from the data. State-of-the-art methods in video are inspired by …