Skip to main content
Artificial Intelligence
Dennis Soemers's user avatar
Dennis Soemers's user avatar
Dennis Soemers's user avatar
Dennis Soemers
Moderator
  • Member for 8 years, 3 months
  • Last seen this week
Profile Activity
Stats
10,479
reputation
383k
reached
209
answers
2
questions
Communities
View all
About

Personal webpage: https://dennissoemers.github.io/

I am currently an Assistant Professor at Maastricht University's Department of Advanced Computing Sciences, where I obtained my Ph.D. in April 2023. My main interests are various domains of AI (such as tree search, game AI, Reinforcement Learning, Machine Learning).

If you found my help useful and wish to buy me a coffee: https://www.buymeacoffee.com/DennisSoemers

Badges
View all badges
2
gold badges
28
silver badges
70
bronze badges
Top tags
View all tags
455
Score
106
Posts
50
Posts %
145
Score
42
Posts
20
Posts %
128
Score
28
Posts
13
Posts %
108
Score
29
Posts
14
Posts %
106
Score
21
Posts
10
Posts %
73
Score
16
Posts
8
Posts %
Top posts
View all questions and answers
answer
19
Why do you not see dropout layers on reinforcement learning examples?
Oct 7, 2018
answer
18
Are there other approaches to deal with variable action spaces?
Dec 13, 2018
answer
18
What is the difference between actor-critic and advantage actor-critic?
Aug 4, 2018
answer
14
What does the symbol $\mathbb E$ mean in these equations?
Aug 27, 2019
answer
13
Why is the derivative of this objective function 0 if the policy is deterministic?
Sep 6, 2018
answer
12
Why does the "reward to go" trick in policy gradient methods work?
Feb 2, 2019
answer
11
Why are lambda returns so rarely used in policy gradients?
Jan 18, 2019
answer
11
Loss jumps abruptly when I decay the learning rate with Adam optimizer in PyTorch
Sep 21, 2018
question
11
How can AI researchers avoid "overfitting" to commonly-used benchmarks as a community?
Aug 12, 2018
answer
10
Does Monte Carlo tree search qualify as machine learning?
Aug 16, 2018
Top Meta posts
6
35
14
Artificial Intelligence is Graduating (Becoming Full, Non-Beta Site)
14
Are questions about prompt-design on-topic here?
6
Announcement: Upcoming Moderator Election Planned for May 9
6
Should I put a disclaimer while answering with low confidence?
6
Answer deleted by diamond moderator during bounty
Top network posts
View all network posts
76
What is the difference between Q-learning and SARSA?
36
How should Feature Selection and Hyperparameter optimization be ordered in the machine learning pipeline?
31
How to effectively make use of a GPU for reinforcement learning?
25
List all environment id in openai gym
25
Why $P(A|B) \neq P(A | B,C) + P(A | B, \neg C)$?