2
votes
How to find the gradient when a black box I/O function is involved in evaluation of the loss?
It's not possible to learn $NN_{pi}$ without (at least approx.) knowing $\mathbf F$. You can approximate the derivative of $\mathbf
F$ wrt the output of the neural network, say $o$, numerically. ...
2
votes
Accepted
How do find the best arm in a multi-armed bandit when exploitation is unimportant?
This answer is relevant to your question.
If you are interested in minimizing the number of pulls to identify the best arm the setting you want to use is Best Arm Identification. In this setting, you ...
1
vote
How to find the gradient when a black box I/O function is involved in evaluation of the loss?
It is always possible to reframe model-fitting problems as reinforcement learning problems. The actions are the choice of model parameters and the reward is the negative of the error (here loss) ...
1
vote
How to find the gradient when a black box I/O function is involved in evaluation of the loss?
Here are two methods you can use.
Numerical derivative
As @gunes explains, you can estimate the gradient of $F$ using numerical differentiation methods, such as finite differences. In particular, the ...
Only top scored, non community-wiki answers of a minimum length are eligible
Related Tags
reinforcement-learning × 1034machine-learning × 346
neural-networks × 267
q-learning × 155
markov-process × 73
multiarmed-bandit × 69
optimization × 42
policy-gradient × 39
artificial-intelligence × 33
monte-carlo × 30
markov-decision-process × 28
mathematical-statistics × 25
gradient-descent × 23
python × 21
probability × 19
terminology × 16
games × 16
contextual-bandit × 16
tensorflow × 15
actor-critic × 15
algorithms × 14
expected-value × 13
convergence × 13
supervised-learning × 13
importance-sampling × 13