Progress for week 50 (2019)
From Robin
(Difference between revisions)
Wonhol (Talk | contribs)
(Ny side: == Wonho == === Accounting === * Have been running risi's multilayered HyperNEAT tweaking parameters to get better result ** initial approach with input - current upper joint position did n…)
Newer edit →
(Ny side: == Wonho == === Accounting === * Have been running risi's multilayered HyperNEAT tweaking parameters to get better result ** initial approach with input - current upper joint position did n…)
Newer edit →
Revision as of 11:22, 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
- Implement Novelty search - how to define behavior metrics?