Incremental Learning of Goal-Directed Actions in a Dynamic Environment by a Robot Using Active Inference
This study investigated how a physical robot can adapt goal-directed actions in dynamically changing environments, in real-time, using an active inference-based approach with incremental learning from human tutoring examples. Using our active inference-based model, while good generalization can be a...
Main Authors: | Takazumi Matsumoto, Wataru Ohata, Jun Tani |
---|---|
Format: | Article |
Language: | English |
Published: |
MDPI AG
2023-10-01
|
Series: | Entropy |
Subjects: | |
Online Access: | https://www.mdpi.com/1099-4300/25/11/1506 |
Similar Items
-
Goal-Directed Planning and Goal Understanding by Extended Active Inference: Evaluation through Simulated and Physical Robot Experiments
by: Takazumi Matsumoto, et al.
Published: (2022-03-01) -
Goal-Directed Planning for Habituated Agents by Active Inference Using a Variational Recurrent Neural Network
by: Takazumi Matsumoto, et al.
Published: (2020-05-01) -
Inference of affordances and active motor control in simulated agents
by: Fedor Scholz, et al.
Published: (2022-08-01) -
Premotor cortex is critical for goal-directed actions
by: Christina eGremel, et al.
Published: (2013-08-01) -
Editorial: Infants' Understanding and Production of Goal-Directed Actions in the Context of Social and Object-Related Interactions
by: Daniela Corbetta, et al.
Published: (2017-05-01)