New answers tagged algorithm-request
4
votes
Accepted
Is there a standardized method to train a reinforcement learning NN by demonstration?
Yes, this is known as imitation learning, which can be divided into
inverse RL (i.e. learn a reward function from demonstrations, then apply RL), and
behaviour cloning (supervised learning applied to ...
1
vote
Compare Strings composed from 2-3 words using NLP/ML(Python)
You can use a model to create rich embeddings for example: sentence transformers and then use cosine similarity distance from sklearn with a threshold (at least 0.6) to create clusters of semantically-...
0
votes
Which RL algorithm should I use to learn an optimal weight vector?
My friend propose local random search:
Initialize:
$W_0 = (0.5,...,0.5)$
step = 0.1, $K < N$, MAX_ITERATIONS
Each iteration:
$W_{new}$ <- $W$
randomly choose up to $K$ weights, change each ...
Top 50 recent answers are included
Related Tags
algorithm-request × 103machine-learning × 26
reference-request × 26
reinforcement-learning × 20
model-request × 20
neural-networks × 16
computer-vision × 9
game-ai × 8
object-detection × 7
deep-learning × 6
unsupervised-learning × 6
clustering × 6
convolutional-neural-networks × 5
natural-language-processing × 5
classification × 5
python × 4
image-recognition × 4
optimization × 4
pattern-recognition × 4
ai-design × 3
genetic-algorithms × 3
image-processing × 3
time-series × 3
image-segmentation × 3
state-of-the-art × 3