Developing Grounded Goals Through Instant Replay Learning
Document Type
Poster Session
Publication Date
9-20-2017
Published In
7th Joint IEEE International Conference On Development And Learning And On Epigenetic Robotics
Abstract
This paper describes and tests a developmental architecture that enables a robot to explore its world, to find and remember interesting states, to associate these states with grounded goal representations, and to generate action sequences so that it can re-visit these states of interest. The model is composed of feed-forward neural networks that learn to make predictions at two levels through a dual mechanism of motor babbling for discovering the interesting goal states and instant replay learning for developing the grounded goal representations. We compare the performance of the model with grounded goal representations versus random goal representations, and find that it is significantly better at re-visiting the goal states when using grounded goal representations.
Conference
7th Joint IEEE International Conference On Development And Learning And On Epigenetic Robotics
Conference Dates
September 18-21, 2017
Conference Location
Lisbon, Portugal
Recommended Citation
Lisa A. Meeden and D. Blank.
(2017).
"Developing Grounded Goals Through Instant Replay Learning".
7th Joint IEEE International Conference On Development And Learning And On Epigenetic Robotics.
https://works.swarthmore.edu/fac-comp-sci/83