David Ireland

Member for 2 years, 11 months
Last seen this week

Summary

Reputation

4,420

4.4k
4.2k
4k

Jul
Oct
Jan
Apr

Top tag

reinforcement-learning

Next privilege

5,000 Rep.

Access to site analytics

Badges

1

5

25

Newest

Caucus

Next badge

0/1

Excavator

Answers

View all 113 answers

Score Activity Newest

18

What exactly are the "parameters" in GPT-3's 175 billion parameters and how are they chosen/generated?

Jul 28, 2020

9

What exactly is the advantage of double DQN over DQN?

Jul 30, 2020

9

Why does the state-action value function, defined as an expected value of the reward and state value function, not need to follow a policy?

Jun 6, 2020

8

Are Q-learning and SARSA the same when action selection is greedy?

May 11, 2020

7

What does the notation $\mathcal{N}(z; \mu, \sigma)$ stand for in statistics?

Aug 23, 2020

Questions

View all 10 questions

Score Activity Newest Views

4

Why do we discount the state distribution?

Apr 6, 2021

3

Why we don't use importance sampling in tabular Q-Learning?

Jun 13, 2020

3

Why is learning $s'$ from $s,a$ a kernel density estimation problem but learning $r$ from $s,a$ is just regression?

May 29, 2020

2

Are the final states not being updated in this $n$-step Q-Learning algorithm?

Jun 2, 2020

2

In Batch Normalisation, are $\hat{\mu}$, $\hat{\sigma}$ the mean and stdev of the original mini-batch or of the input into the current layer?

Jun 7, 2020

Tags

View all 122 tags

reinforcement-learning

228

Score

99

posts

q-learning

85

Score

30

posts

deep-rl

57

Score

22

posts

dqn

54

Score

20

posts

comparison

39

Score

10

posts

Reputation

+10

Q learning: Action is combination of two actions

+10

Reinforcement learning with action consisting of two discrete values

+60

What exactly are the "parameters" in GPT-3's 175 billion parameters and how are they chosen/generated?

+10

Why do we discount the state distribution?

Badges

View all badges

1

gold badge

Fanatic

Aug 14, 2020

5

silver badges

Civic Duty

Apr 23, 2021
Enlightened

Aug 12
Enthusiast

Jun 5, 2020

25

bronze badges

reinforcement-learning

Aug 28, 2020
Talkative

Jan 8, 2021
Self-Learner

Nov 15, 2020

Accounts

View all 12 accounts

Artificial Intelligence

4,420
1
5
25

Operations Research

333
1
7

145
6

119
6

Cross Validated

111
2

Active bounties (0)

Active Offered Earned

This user has no active bounties

Votes cast

443

upvotes

106

downvotes

283

question votes

266

answer votes