Showing versus doing: Teaching by demonstration

By Mark K. Ho, Michael L. Littman, James MacGlashan, Fiery Cushman, Joseph L. Austerweil. 2016

118 citations recorded by the source corpus.

How researchers see this paper

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

Citations in the corpus

Human-in-the-Loop Imitation Learning using Remote Teleoperation (2020, background): “Other paradigms for human-in-the-loop policy learning include collaboration [14, 15], teaching the robot through informative sample selection [7, 9, 17], and leveraging physical kinesthetic corrections [5, 6].”
Leveraging Human Guidance for Deep Reinforcement Learning Tasks (2019, background): “They further showed that imitation learning algorithm can beneﬁt substantially more from the data collected in the showing mode [Ho et al. , 2016].”
Observational Learning by Reinforcement Learning (2017, methodology): “e behaviour of other agents [16, 17] and then use this, in conjunction with RL techniques, to optimize this inferred function. While these methods have been successfully applied to a variety of tasks [14, 18, 19, 20, 21, 22, 23, 24, 25], one problematic aspect of both these scenarios is that they al”
Counterfactual Data-Fusion for Online Reinforcement Learners (2017, background): “Others have studied scenarios in which agents learn from expert teachers in the inverse reinforcement learning problems [1, 9].”
Learning to Teach (2018, background): “…another literature called ‘pedagogical teaching’ (Shafto et al., 2014), especially its application to inverse reinforcement learning (IRL) (Ho et al., 2016) is much closer to our setting in that the teacher adjusts its behavior in order to facilitate student learning, by communicating…”
Learning to Reweight with Deep Interactions (2021, background): “The concept of teaching can be found in label propagation (Gong et al. 2016a,b), pedagogical teaching (Ho et al. 2016; Shafto, Good-man, and Grifﬁths 2014), etc. (Liu et al. 2017) leverages a teaching way to speed up the training, where the teacher model selects the training data balancing the…”
Learning to Teach with Dynamic Loss Functions (2018, background): “Furthermore there are research on pedagogical teaching inspired from cognitive science [44, 23, 39] in which a teacher module is responsible for providing informative examples to the learner for the sake of understanding a concept rapidly.”
Theory of Mind and Preference Learning at the Interface of Cognitive Science, Neuroscience, and AI: A Review (2022, background): “Ho et al. (2016) have shown that humans tend to be pedagogic when teaching, picking trajectories that help disambiguate their preferences, rather than optimal ones for the task.”