Skip to main content
Artificial Intelligence
Federico Taschin's user avatar
Federico Taschin's user avatar
Federico Taschin's user avatar
Federico Taschin
  • Member for 4 years, 11 months
  • Last seen more than a month ago
Profile Activity
Stats
253
reputation
5k
reached
0
answers
5
questions
Communities
View all
About

I have a degree in Computer Engineering from the University of Padova, Italy. I am now studying Machine Learning at KTH Royal Institute of Technology, with focus on Reinforcement Learning.

Badges
This user doesn’t have any gold badges yet.
2
silver badges
7
bronze badges
Top tags
View all tags
0
Score
4
Posts
80
Posts %
0
Score
2
Posts
40
Posts %
0
Score
2
Posts
40
Posts %
0
Score
2
Posts
40
Posts %
0
Score
1
Posts
20
Posts %
0
Score
1
Posts
20
Posts %
Top posts
question
8
Why is KL divergence used so often in Machine Learning?
Dec 15, 2020
question
3
When learning off-policy with multi-step returns, why do we use the current behaviour policy in importance sampling?
Nov 16, 2020
question
2
How to derive matrix form of the Bellman operators?
Dec 24, 2020
question
1
Control algorithms when system dynamics are stochastic and/or unknown
Feb 7
question
1
How to compute the Retrace target for multi-step off-policy Reinforcement Learning?
Nov 27, 2020
Top network posts
View all network posts
109
Room cannot find implementation
10
Convert from URI to Uri and the other way around
9
PyTorch mutiprocessing: Do I need to use Lock() when accessing a shared model?
7
JAX Apply function only on slice of array under jit
6
Docker build failed: tag invalid reference format (Gitlab CI)