Feedforward Closedloop Learning (FCL)
Project description
Feedforward closed loop learning (FCL) is a learning algorithm which adds flexibility to autonomous agents.
A designer defines an initial behaviour as a reflex and then FCL learns from the reflex to develop new flexible behaviours.
The Python documentation can be obtained with:
import feedforward_closedloop_learning as fcl help(fcl)
The Python API is identical to the C++ API: The header files fcl.h, neuron.h and layer.h contain docstrings for all important calls. The doxygen generated documentation can be found here: https://github.com/glasgowneuro/feedforward_closedloop_learning/tree/master/docs
The best way to get started is to look at the script in tests_py: https://github.com/glasgowneuro/feedforward_closedloop_learning/tree/master/tests_py
A full application using the Python API is our vizdoom agent: https://github.com/glasgowneuro/fcl_demos
Project details
Download files
Download the file for your platform. If you're not sure which to choose, learn more about installing packages.
Source Distribution
Built Distribution
Hashes for feedforward_closedloop_learning-1.2.4.tar.gz
Algorithm | Hash digest | |
---|---|---|
SHA256 | 6e9c979a62c326e34b4e70407f51e71986f7a7678c84089a954969982b73e4f8 |
|
MD5 | 23935c03d1b9d31dfd68284b9d8abd05 |
|
BLAKE2b-256 | 0081ffeba9d1aaa0ff2b318758147bdb711a6992d9bde424c76d585b6202f50c |
Hashes for feedforward_closedloop_learning-1.2.4-cp36-cp36m-win_amd64.whl
Algorithm | Hash digest | |
---|---|---|
SHA256 | bfc2b84f4400ffcc07bfadb1387e7de4a2b7ad355765a7dd6af42d953df1a90c |
|
MD5 | 81cec80b9a0c252aa60e04cbb0ee293a |
|
BLAKE2b-256 | edba003aafbfaa4f260b5b1d1ec1dba425094907c82202b10ccce1548cdb10bf |