Robot Learning from Human Teachers

By Sonia Chernova, Andrea Lockerd Thomaz. 2014

281 citations recorded by the source corpus.

Subfields: Artificial Intelligence, Control and Systems Engineering, Reinforcement Learning

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

In Control and Systems Engineering

In Reinforcement Learning

Citations in the corpus

What can the brain teach us about building artificial intelligence? (2016, background): “The recent startling improvements in computer vision (Krizhevsky, Sutskever, & Hinton, 2012), machine translation (Johnson et al., 2016), and question answering (Weston et al, 2015) were possible, precisely because they avoided these limitations by foregoing symbolic compositionality altogether.”
Imitating Latent Policies from Observation (2018, background): “This approach has an extensive breadth of applications and a long history of research, ranging from early successes in autonomous driving [18], to applications in robotics [20, 4] and software agents (e.g. [23, 14]).”
Interactively shaping robot behaviour with unlabeled human instructions (2019, background): “By contrast, interactive learning relies on human teaching signals for guiding the robot throughout the learning process [6].”
Recent Advances in Robot Learning from Demonstration (2020, background): “Bullard K, Thomaz AL, Chernova S. 2018.”
State Aware Imitation Learning (2017, background): “Success stories are numerous in the ﬁeld of robotics [3] where imitation learning has long been subject of research but can also be found in software domains with recent success stories including AlphaGo [23] which learns to play the game of Go from a database of expert games before improving…”
Deliberation for autonomous robots: A survey (2017, background): “The recent book of [42] proposes future directions of research.”
Generative predecessor models for sample-efficient imitation learning (2019, methodology): “For each scenario, we provide 20 demonstrations using kinesthetic teaching, which constitutes a natural way of recording demonstrations but provides state-trajectories only (Chernova and Thomaz, 2014).”
A survey of robot learning from demonstrations for Human-Robot Collaboration (2017, background): “Therefore, to date, there are few studies that have investigated LfD based learning for teaching complex human-robot collaborative tasks to a robot [3].”
The EMPATHIC Framework for Task Learning from Implicit Human Feedback (2020, background): “We view learning from implicit human feedback (LIHF) as complementary to learning from explicit human teaching, which might take the form of demonstrations [1], evaluative feedback [2, 3], or other communicative modalities [4, 5, 6, 7, 8].”
Learning From Explanations Using Sentiment and Advice in RL (2017, unknown): “explanations, demonstrations, and critique [4].”