Ernest 10.5 is similar to Ernest 10.4 except that he constructs bundles to represent other Ernests. These bundles become attractive when he discovers that he can cuddle with other Ernests (same principle as with food).
Ernest 10.4 has an improved local-space memory and an improved bundle construction mechanism (see our discussion on bundles here).
On step 188, there is no more fish within the range of Ernest's vision nor within its tactile perception, but Ernest is still aware of the presence of a fish behind him. His local-space awareness makes him turn back towards that fish.
Note that Ernest's spatial awareness is still local: when he is in the lower part of the board, he is unaware of the presence of fish in the upper part of the board.
We kept Ernest's algorithm in Java. We developed a NetLog extension to access Ernest's java algorithm from within NetLogo. We called this extension IMOS (Intrinsic MOtivation System). Like the Ernest algorithm, IMOS is open source. We are happy to share it and provide all necessary support.
IMOS allows you to easily include environment-agnostic intrinsically motivated agents in your NetLogo models.
Ernest 10.3 works as well in a continuous space. This again demonstrates the robustness of the algorithm.
In this experiment, however, the time is still "discrete": Ernest 10.3 cannot turn while he is still moving forward or vice versa. We now need to investigate what happens if the next action can be triggered before the previous action was completed.
Also, we are still investigating how Ernest can construct a representation of his surrounding space. This should be easier in a continuous space than in a grid because all directions appear equivalent.
This continuous version of the environment was developed by Simon Gay.
You can now interact with Ernest 10.3 in 3D (better with Chrome but works also with Firefox
—
requires a recent graphic processing unit).
The 3D environment is called SECA for Simulated Environment for Constructivist Agents. SECA was developed by Olivier Voisin as part of his master thesis.
Abstract-Lite offers an interactive interface to visualize your activity traces. It relies on XPATH instructions and XSL stylesheets to help you customize your visualizations. Abstract-Lite can display your traces in real time. For an example, see Ernest 10.3's trace.
This is the main paper that presents Ernest's algorithm. Specifically, the paper provides a detailed presentation of Ernest 7.2 and discusses the implications for the study of emergent cognition.
This 6-page paper reports Ernest 9.1's experiment and discusses how Ernest learns early-stage sensorimotor and spatial regularities. The paper also introduces Ernest 9's cognitive architecture.
Posts
