Episode #125 of the Stack Overflow podcast is here. We talk Tilde Club and mechanical keyboards. Listen now

Profile Activity

Dennis Soemers

Network profile

Reputation

5,157

5.2k
3.9k
2.6k

Jan
Apr
Jul
Oct

Next tag badge

machine-learning

55/100 score

21/20 answers

Badges

1

7

39

Newest

Yearling

Next badge

57/80

Impact

39 posts edited

57 helpful flags

485 votes cast

Summary Answers Questions Tags Badges Favorites Bounties Reputation All actions

Answers (161)

Votes Activity Newest

9	Why is the derivative 0 if the policy is deterministic?
8	Keeping track of visited states in Breadth-first Search
7	What is the difference between Actor-Critic and Advantage Actor-Critic?
7	Loss jumps abruptly when I decay the learning rate with Adam optimizer in PyTorch
6	What does the symbol $\mathbb E$ mean in these equations?

View more →

Reputation (5,157)

+10	What tools are used to deal with adversarial examples problem?
+10	Why do you not see dropout layers on reinforcement learning examples?
+10	How would one implement a multi-agent environment with asynchronous action and rewards per agent?
+10	How do you calculate the heuristic value in this specific case?

View more →

Questions (2)

Votes Activity Newest

5	How can AI researchers avoid “overfitting” to commonly-used benchmarks as a community?
1	Is it common in RL research with Atari/ALE to automatically press FIRE to start games?

Tags (138)

195 reinforcement-learning × 81	41 neural-networks × 20
55 machine-learning × 21	35 deep-learning × 16
51 q-learning × 16	31 math × 10
47 monte-carlo-tree-search × 23	24 algorithm × 9
45 game-ai × 23	23 ai-design × 7

View more →

Accounts (29)

	Stack Overflow	5,417 rep	2 gold badges15 silver badges38 bronze badges
	Artificial Intelligence	5,157 rep	1 gold badge7 silver badges39 bronze badges
	Cross Validated	1,543 rep	1 gold badge6 silver badges18 bronze badges
	Academia	346 rep	1 gold badge3 silver badges8 bronze badges
	Computer Science	251 rep	2 silver badges9 bronze badges

Badges (31)

Recent Class Name

Yearling × 3	reinforcement-learning
Talkative	Proofreader
Revival × 10	Civic Duty
Necromancer	Nice Answer
Convention	Cleanup

View more →

Active bounties (0)

Active Offered Earned

This user has no active bounties

Votes cast (485)

all time			by type			month
463	up		168	question		1
22	down		317	answer		1

Artificial Intelligence Stack Exchange works best with JavaScript enabled