Progress for week 50 (2019)

From Robin

Contents 1 Wonho 1.1 Accounting 1.2 Budget 2 Tony 2.1 Accounting 2.2 Budget

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

Fil:ctrnn.png

Budget

• tweaking fitness function
• Implement simple CPG circuit
• Implement Novelty search - how to define behavior metrics?
  • No ready-to-use package available in python
  • Can map-elites be something relevant here?

Tony

Accounting

• Found a fitness-function, but it needs some tweaking for my problem
• Genetic algorithm is working with DEAP, so I can now simulate

Budget

• Ha Juleferie
  • Begynne å skrive introduction/background
  • Begynne å skrive Eksperimenter og hva jeg har gjort hittil