Chukwudi

Unregistered

Member for 3 years, 6 months
Last seen more than 3 years ago

Network profile

Summary

Reputation

359

359
339
319

Mar
Jun
Sep
Dec

Top tag

reinforcement-learning

Next privilege

500 Rep.

Cast close & reopen votes

Badges

2

7

Newest

Notable Question

Next badge

0/1

Custodian

Questions

View all 14 questions

Score Activity Newest Views

11

What exactly is the advantage of double DQN over DQN?

Jul 30, 2020

5

Why do DQNs tend to forget?

Jul 27, 2020

3

Why is it not advisable to have a 100 percent exploration rate?

Jun 26, 2020

2

Why isn't it wise for us to completely erase our old Q value and replace it with the calculated Q value?

Jun 26, 2020

2

Why is 100% exploration bad during the learning stage in reinforcement learning?

Jun 29, 2020

Answers

Score Activity Newest

0

Does "transition model" alone in an MDP imply it's non-deterministic?

Jun 26, 2020

Tags

View all 17 tags

reinforcement-learning

0

Score

14

posts

q-learning

0

Score

10

posts

deep-rl

0

Score

6

posts

dqn

0

Score

6

posts

exploration-exploitation-tradeoff

0

Score

5

posts

Reputation

+10

Why do DQNs tend to forget?

+80

What exactly is the advantage of double DQN over DQN?

+10

How can deep Q-learning converge if the targets may not be correct?

+10

What happens if our target network overestimates the value?

Badges

View all badges

This user doesn’t have any gold badges yet.

2

silver badges

Notable Question

Apr 30
Yearling

Jun 12, 2021

7

bronze badges

Curious

Jul 31, 2020
Nice Question

Apr 2
Commentator

Jun 14, 2020

Accounts

Artificial Intelligence

359
2
7

Active bounties (0)

Active Offered Earned

This user has no active bounties

Votes cast

This user has not cast any votes