Re:Deep reinforcement learning is a waste of time (2019)
by jeeeb on Sunday July 11, 2021 @12:19AM
(#27798443)
> Though maybe I'm missing something 'cos it seems to me you can run gradient descend on non-differentiable functions
Isn't that exactly the point though? If you don't have an analytical solution for the gradient of the loss (reward) wrt the parameters - yes - you could brute force a numerical solution but as the number of parameters grows that quickly becomes infeasible. Approaches such as RL and GA provide a more intelligent way to search the parameter space.
Re:Deep reinforcement learning is a waste of time (2019)
by LeegleechN on Saturday July 10, 2021 @07:24PM
(#27797183)
Neural network models have millions of parameters, which means you are trying to optimize in spaces with millions of dimensions. If you can't use differentiation you get hit really hard with the curse of dimensionality.
Differentiable functions are great because you can run gradient descent on them in a very optimized way. Example: if your objective is to have a very high value, search in the direction that has a mounting slope.
Though maybe I'm missing something 'cos it seems to me you can run gradient descend on non-differentiable functions. It just requires more evaluations.