WhiteICE version information: Difference between revisions

From Hosaka/WhiteICE wiki
Jump to navigation Jump to search
Content deleted Content added
No edit summary
No edit summary
Line 1: Line 1:
<strong>WhiteICE v1.39b</strong>
<strong>WhiteICE v1.39b (in development)</strong>


New version with improved RL algorithm that give more often positive results (in many hours long stimulation). Stimulation interval is 5000ms. Effect seem to vary between 1-5% (average distance change)
New version with improved RL algorithm that SHOULD give more often positive results (in many hours long stimulation). Stimulation interval is 1000ms. Effect seem to be only about 1% with this new code.


Program learns very slowly, 3h 20minutes (300 models) didn’t show big improvements. Try to increase tau from 0.02 to 0.1 and see if it still increases performance a bit.
Program learns very slowly, 3h 20minutes (300 models) didn’t show big improvements. Try to increase tau from 0.02 to 0.1 and see if it still increases performance a bit. => tau increase seem to give worse results???


<strong>WhiteICE v1.38b</strong>
<strong>WhiteICE v1.38b</strong>

Revision as of 21:15, 6 July 2026

WhiteICE v1.39b (in development)

New version with improved RL algorithm that SHOULD give more often positive results (in many hours long stimulation). Stimulation interval is 1000ms. Effect seem to be only about 1% with this new code.

Program learns very slowly, 3h 20minutes (300 models) didn’t show big improvements. Try to increase tau from 0.02 to 0.1 and see if it still increases performance a bit. => tau increase seem to give worse results???

WhiteICE v1.38b

This version re-enabled longer stimulation interval 5000ms which seem to have positive effect to "episodes-result.txt" average reinforcement value time-series when stimulatio is run for many hours. Typical effect seem to be 5% (versus random stimulation)

WhiteICE v1.37b

This experimental version used very short stimulation interval 500ms.