Progress for week 50 (2019)
From Robin
(Difference between revisions)
(→Wonho) |
(→Wonho) |
||
| Line 5: | Line 5: | ||
** changed input to network to sinusoid -> now capable of generating dynamic gaits, but not much successful walking gaits | ** changed input to network to sinusoid -> now capable of generating dynamic gaits, but not much successful walking gaits | ||
=== Budget === | === Budget === | ||
| + | * tweaking fitness function | ||
* Implement Novelty search - how to define behavior metrics? | * Implement Novelty search - how to define behavior metrics? | ||
** No ready-to-use package available in python | ** No ready-to-use package available in python | ||
** Can map-elites be something relevant here? | ** Can map-elites be something relevant here? | ||
Revision as of 11:39, 16 December 2019
Wonho
Accounting
- Have been running risi's multilayered HyperNEAT tweaking parameters to get better result
- initial approach with input - current upper joint position did not manage to get dynamic response in CTRNN
- changed input to network to sinusoid -> now capable of generating dynamic gaits, but not much successful walking gaits
Budget
- tweaking fitness function
- Implement Novelty search - how to define behavior metrics?
- No ready-to-use package available in python
- Can map-elites be something relevant here?
