Progress for week 50 (2019)

Fra Robin

(Forskjeller mellom versjoner)
Gå til: navigasjon, søk
(Wonho)
(Wonho)
Linje 5: Linje 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?

Versjonen fra 16. des 2019 kl. 11:39

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?
Personlige verktøy