Imitation Learning as Cause-Effect Reasoning
نویسندگان
چکیده
We propose a framework for general-purpose imitation learning centered on cause-effect reasoning. Our approach infers a hierarchical representation of a demonstrator’s intentions, which can explain why they acted as they did. This enables rapid generalization of the observed actions to new situations. We employ a novel causal inference algorithm with formal guarantees and connections to automated planning. Our approach is implemented and validated empirically using a physical robot, which successfully generalizes skills involving bimanual manipulation of composite objects in 3D. These results suggest that cause-effect reasoning is an effective unifying principle for cognitive-level imitation learning.
منابع مشابه
A Novel Parsimonious Cause-Effect Reasoning Algorithm for Robot Imitation and Plan Recognition
Manually programming robots is difficult, impeding more widespread use of robotic systems. In response, efforts are being made to develop robots that use imitation learning. With such systems a robot learns by watching humans perform tasks. However, most imitation learning systems replicate a demonstrator’s actions rather than obtaining a deeper understanding of why those actions occurred. Here...
متن کاملA Case-Based Approach To Imitation Learning in Robotic Agents
Learning by imitation is an essential process in human cognition. Recently, imitation learning has also become important in robotics research. We address the problem of learning by imitation in interactive, robotic agents using case-based reasoning. We describe two tasks for which case-based reasoning may be used: (i) interpretation, in which the robot interprets new skill demonstrations as bei...
متن کاملExamining functional mechanisms of imitative learning in infancy: does teleological reasoning affect infants' imitation beyond motor resonance?
Recently, researchers have been debating whether infants' selective imitative learning is primarily based on sensorimotor processes (e.g., motor resonance through action perception) or whether inferential processes such as teleological reasoning (i.e., reasoning about the efficiency of others' actions) predominantly explain selective imitation in infancy. The current study directly investigated...
متن کاملCause and Intent: Social Reasoning in Causal Learning
The acquisition of causal knowledge is a primary goal of childhood; yet most of this knowledge is known already to adults. We argue that causal learning which leverages social reasoning is a rapid and important route to knowledge. We present a computational model integrating knowledge about causality with knowledge about intentional agency, but using a domaingeneral mechanism for reasoning. Inf...
متن کاملLearning by Imitation, Reinforcement and Verbal Rules in Problem Solving Tasks
Learning by imitation is a powerful process for acquiring new knowledge, but there has been little research exploring imitation’s potential in the problem solving domain. Classical problem solving techniques tend to center around reinforcement learning, which requires significant trial-and-error learning to reach successful goals and problem solutions. Heuristics, hints, and reasoning by analog...
متن کامل