Watch what I do: programming by demonstration

By A. Cypher, Daniel C. Halbert, David J. Kurlander, Henry Lieberman, D. Maulsby, Brad A. Myers, Alan Turransky. 1993

How researchers see this paper

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

1. Percy Liang
2. Yoshua Bengio
3. Mohit Bansal
4. Sergey Levine
5. Graham Neubig
6. Quoc V. Le
7. Zhe Gan
8. Jianfeng Gao

Citations in the corpus

• Learning to Optimize (2016, background): “A different line of work, known as “programming by demonstration” [7], considers the problem of learning programs from examples of input and output.”
• Interacting meaningfully with machine learning systems: Three experiments (2009, background): “A large body of work employing user feedback falls under the topic of programming by demonstration, which enables a system to learn a procedural program interactively from user demonstrations (Cypher, 1993; McDaniel and Myers, 1999; Lieberman, 2001).”
• A Decision-Theoretic Model of Assistance (2007, background): “This work is also closely related to learning from demonstration or programming by demonstration (Atkeson & Schaal, 1997; Cypher, 1993; Lau, Wolfman, Domingos, & Weld, 2003).”
• Programming by Demonstration Using Version Space Algebra (2003, background): “Programming by demonstration (PBD) has the potential to bridge the gap between programmers and non-programmers, and allow anyone to automate repetitive, everyday tasks (Cypher, 1993; Lieberman, 2001).”
• Dimensions in program synthesis (2010, unknown): “Traces are an appropriate model for programming by demonstration systems for end-users [13], where the intermediate states resulting from the user’s successive actions on a user interface constitute a valid trace.”
• Personalised hypermedia presentation techniques for improving online customer relationships (2001, background): “A number of early systems that observe user behaviours and learn action sequences are described in Cypher (1993) along with descriptions of the tasks they perform.”
• Accelerating Reinforcement Learning through Implicit Imitation (2003, background): “Learning apprentices are closely related to programming by demonstration systems (Lieberman, 1993).”
• A Dynamical System-based Approach to Modeling Stable Robot Control Policies via Imitation Learning (2012, methodology): “Imitation learning has been used for various applications including: software development (Cypher, 1993; Lieberman, 2001; Mitchell et al., 1994), symbolic learning and reasoning (Lozano-Perez, 1983; Hovland et al.”
• Learning Programs: A Hierarchical Bayesian Approach (2010, background): “To motivate this direction of exploration, consider programming by demonstration (PBD) (Cypher, 1993).”
• Program Synthesis Using Natural Language (2015, background): “For PBD these domains include text manipulation [28] and table transformations [23] among others [7].”
• Making mashups with marmite: towards end-user programming for the web (2007, background): “For example, Cypher [5] and Lieberman [20] describe numerous programming-by-demonstration and programming-by-example systems.”
• Learning to Solve Complex Tasks by Talking to Agents (2021, background): “While in practice many program synthesis problems and related problems in programming by example (Kurlander et al., 1993) involve executing programs across mixtures of sources (similar in spirit to our goal of modeling agent interaction), like with semantic parsing, such work is often limited to…”
• Program Synthesis (2017, background): “Traces are an appropriate model for programming by demonstration systems [25], where the intermediate states resulting from the user’s successive actions on a user interface constitute a valid trace.”