Deep Reinforcement Learning of Abstract Reasoning from Demonstrations

Extracting a set of generalizable rules that govern the dynamics of complex, high-level interactions between humans based only on observations is a high-level cognitive ability. Mastery of this skill marks a significant milestone in the human developmental process. A key challenge in designing such...

Celý popis

Uloženo v:
Podrobná bibliografie
Vydáno v:2018 13th ACM/IEEE International Conference on Human-Robot Interaction (HRI) s. 160 - 168
Hlavní autoři: Clark-Turner, Madison, Begum, Momotaz
Médium: Konferenční příspěvek
Jazyk:angličtina
Vydáno: New York, NY, USA ACM 26.02.2018
Edice:ACM Conferences
Témata:
Abstract Reasoning
Analytical models
Cognition
Computing methodologies > Artificial intelligence > Computer vision > Computer vision tasks > Vision for robotics
Computing methodologies > Artificial intelligence > Knowledge representation and reasoning
Computing methodologies > Artificial intelligence > Knowledge representation and reasoning > Cognitive robotics
Computing methodologies > Machine learning > Learning paradigms > Supervised learning
Deep Learning
Human-robot interaction
Learning from Demonstration
Object recognition
Probabilistic logic
Reinforcement learning
Theory of computation > Logic > Abstraction
Theory of computation > Logic > Automated reasoning
Training
deep learning
abstract reasoning
learning from demonstration
ISBN:9781450349536, 1450349536
ISSN:2167-2148
On-line přístup:Získat plný text
Tagy: Přidat tag
Žádné tagy, Buďte první, kdo vytvoří štítek k tomuto záznamu!
Popis
Shrnutí:Extracting a set of generalizable rules that govern the dynamics of complex, high-level interactions between humans based only on observations is a high-level cognitive ability. Mastery of this skill marks a significant milestone in the human developmental process. A key challenge in designing such an ability in autonomous robots is discovering the relationships among discriminatory features. Identifying features in natural scenes that are representative of a particular event or interaction (i.e. »discriminatory features») and then discovering the relationships (e.g., temporal/spatial/spatio-temporal/causal) among those features in the form of generalized rules are non-trivial problems. They often appear as a »chicken-and-egg» dilemma. This paper proposes an end-to-end learning framework to tackle these two problems in the context of learning generalized, high-level rules of human interactions from structured demonstrations. We employed our proposed deep reinforcement learning framework to learn a set of rules that govern a behavioral intervention session between two agents based on observations of several instances of the session. We also tested the accuracy of our framework with human subjects in diverse situations.
ISBN:9781450349536
1450349536
ISSN:2167-2148
DOI:10.1145/3171221.3171289