Hi Mohakhachai! Yes, it can depend on a cost estimate, or an urgency estimate. If for example, the children nodes are created using reinforcement learning, they have a value function estimating average future reward, this can be used to pick the best option.
Were at the age where CompSci lectures feature phrases like "Kiting Strategy" :)
awesome talk, thank you ❤❤
And how selector choose best Action depending on or ? Or cost
Or we use random decorator
Or we add new type of decorator
Hi Mohakhachai! Yes, it can depend on a cost estimate, or an urgency estimate. If for example, the children nodes are created using reinforcement learning, they have a value function estimating average future reward, this can be used to pick the best option.