# Tag Info

### Reinforcement Learning - what causes a plateau in the performance of the model during training?

I think I figured it out. Inspired by this post, I basically introduced a learning rate schedule. Essentially, the problem is that the model reaches a point where it needs more fine-tuned changes, but ...
• 1,159

### How does backpropagation work in the case of reinforcement learning for games?

Simply by using Q-Learning. You store the last N input- and output-vectors and on reward/punishment just just train the network by BP on the stored input- and output-vectors. The sign of the learning ...
• 1
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 ...
• 791
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) ...
• 150

### Q-Learning Reward function racing game

"My question is how should is set the reward and the function to get target Q-Value." I think you can only set the reward manually and not the function. Scaling rewards to between 0 and 1, ...
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 ...
• 6,003
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. ...