New answers tagged implementation
0
I figured this out by going to the author's publicly available github code. It turned out the authors were just generating the transition probability $p$ from $\mathcal{N}(\mu,\sigma^2)$ at the beginning of each episode for some reason. Answering it myself for the sake of not leaving this question unanswered.
reinforcement-learning markov-decision-process implementation temporal-difference-methods transition-model
2
The conventions I have seen tend to post-multiply rather than pre-multiply, although there are examples in the literature which adopt the opposite convention.
Some examples include:
In Deep Learning: An Introduction for Applied Mathematicians, a layer with input $x \in \mathbb R^n$ and output $f(x) \in \mathbb R^m$ is computed by
$$ f(x) = \sigma(Wx + b)$$
...
Top 50 recent answers are included
Related Tags
implementation × 66reinforcement-learning × 21
neural-networks × 15
deep-learning × 8
convolutional-neural-networks × 6
dqn × 6
machine-learning × 5
python × 5
papers × 5
tensorflow × 4
deep-rl × 4
backpropagation × 4
comparison × 3
proximal-policy-optimization × 3
policy-evaluation × 3
classification × 2
training × 2
q-learning × 2
keras × 2
recurrent-neural-networks × 2
reference-request × 2
philosophy × 2
loss-functions × 2
generative-adversarial-networks × 2
search × 2