As of May 31, 2023, we have updated our Code of Conduct.
Artificial Intelligence
Todd Sewell's user avatar
Todd Sewell's user avatar
Todd Sewell's user avatar
Todd Sewell
  • Member for 1 year, 4 months
  • Last seen more than a week ago
Profile Activity
Stats
338
reputation
2k
reached
11
answers
0
questions
Communities
View all
Badges
View all badges
This user doesn’t have any gold badges yet.
1
silver badge
7
bronze badges
Top tags
View all tags
12
Score
7
Posts
64
Posts %
11
Score
6
Posts
55
Posts %
4
Score
3
Posts
27
Posts %
4
Score
3
Posts
27
Posts %
4
Score
3
Posts
27
Posts %
3
Score
2
Posts
18
Posts %
Top posts
View all questions and answers
All Questions Answers
Score Newest
answer
3
At what point are MCTS results discarded in AlphaZero Training?
Jan 24, 2022
answer
2
How does policy network learn in AlphaZero?
Aug 20, 2022
answer
2
Neural Network output for the game of Checkers
Oct 29, 2022
answer
2
Reproducing AlphaZero/MuZero: Failed to beat initial model in arena
Apr 8
answer
1
Does AlphaGo play random moves in a real competition?
Jan 23, 2022
answer
1
How are NNs output setup for games that allow multiple actions each turn and have very large sets of possible actions?
Dec 31, 2022
answer
1
Is AlphaZero's output (action probabilities) vector suboptimal?
Jan 2
answer
1
MCTS: How to select children when none of them are visited?
Feb 10
answer
1
Is it possible for AlphaGo Zero to use recurrent networks to achieve similar performance?
Aug 21, 2022
answer
1
In off-policy MC learning, why is the probability of sampling a trajectory the same as having a return?
Oct 4, 2022
Top network posts
View all network posts
52
Was AlphaZero taught castling?
29
Where can you play against AlphaZero?
18
Is switch operator atomic?
14
Best solution for static member being accessed by instance reference
14
Why Kotlin does not allow slash in identifiers

Your privacy

By clicking “Accept all cookies”, you agree Stack Exchange can store cookies on your device and disclose information in accordance with our Cookie Policy.