An overview of machine teaching

X Zhu, A Singla, S Zilles, AN Rafferty - arxiv preprint arxiv:1801.05927, 2018 - arxiv.org
In this paper we try to organize machine teaching as a coherent set of ideas. Each idea is
presented as varying along a dimension. The collection of dimensions then form the …

What matters in learning from offline human demonstrations for robot manipulation

A Mandlekar, D Xu, J Wong, S Nasiriany… - arxiv preprint arxiv …, 2021 - arxiv.org
Imitating human demonstrations is a promising approach to endow robots with various
manipulation capabilities. While recent advances have been made in imitation learning and …

Pebble: Feedback-efficient interactive reinforcement learning via relabeling experience and unsupervised pre-training

K Lee, L Smith, P Abbeel - arxiv preprint arxiv:2106.05091, 2021 - arxiv.org
Conveying complex objectives to reinforcement learning (RL) agents can often be difficult,
involving meticulous design of reward functions that are sufficiently informative yet easy …

[HTML][HTML] Reinforcement learning with human advice: a survey

A Najar, M Chetouani - Frontiers in Robotics and AI, 2021 - frontiersin.org
In this paper, we provide an overview of the existing methods for integrating human advice
into a Reinforcement Learning process. We first propose a taxonomy of the different forms of …

One-shot imitation from observing humans via domain-adaptive meta-learning

T Yu, C Finn, A **e, S Dasari, T Zhang… - arxiv preprint arxiv …, 2018 - arxiv.org
Humans and animals are capable of learning a new behavior by observing others perform
the skill just once. We consider the problem of allowing a robot to do the same--learning …

State entropy maximization with random encoders for efficient exploration

Y Seo, L Chen, J Shin, H Lee… - … on Machine Learning, 2021 - proceedings.mlr.press
Recent exploration methods have proven to be a recipe for improving sample-efficiency in
deep reinforcement learning (RL). However, efficient exploration in high-dimensional …

Better-than-demonstrator imitation learning via automatically-ranked demonstrations

DS Brown, W Goo, S Niekum - Conference on robot learning, 2020 - proceedings.mlr.press
The performance of imitation learning is typically upper-bounded by the performance of the
demonstrator. While recent empirical results demonstrate that ranked demonstrations allow …

[LIVRE][B] Robot learning from human teachers

S Chernova, AL Thomaz - 2022 - books.google.com
Learning from Demonstration (LfD) explores techniques for learning a task policy from
examples provided by a human teacher. The field of LfD has grown into an extensive body …

Avid: Learning multi-stage tasks via pixel-level translation of human videos

L Smith, N Dhawan, M Zhang, P Abbeel… - arxiv preprint arxiv …, 2019 - arxiv.org
Robotic reinforcement learning (RL) holds the promise of enabling robots to learn complex
behaviors through experience. However, realizing this promise for long-horizon tasks in the …

Human-robot mutual adaptation in collaborative tasks: Models and experiments

S Nikolaidis, D Hsu, S Srinivasa - The International Journal …, 2017 - journals.sagepub.com
Adaptation is critical for effective team collaboration. This paper introduces a computational
formalism for mutual adaptation between a robot and a human in collaborative tasks. We …