Raphael
@rsio.bsky.social
Researcher in Cybersecurity. Computer Science PhD candidate. Interested in Penetration Testing and Reinforcement Learning.
Reposted by Raphael
This one's been a long time coming.
In this post on Decisions & Dragons I answer "Should we abandon RL?"
The answer is obviously no, but people ask because they have a fundamental misunderstanding of what RL is.
RL is a problem, not an approach.
www.decisionsanddragons.com/posts/should...
In this post on Decisions & Dragons I answer "Should we abandon RL?"
The answer is obviously no, but people ask because they have a fundamental misunderstanding of what RL is.
RL is a problem, not an approach.
www.decisionsanddragons.com/posts/should...
August 15, 2025 at 11:30 PM
This one's been a long time coming.
In this post on Decisions & Dragons I answer "Should we abandon RL?"
The answer is obviously no, but people ask because they have a fundamental misunderstanding of what RL is.
RL is a problem, not an approach.
www.decisionsanddragons.com/posts/should...
In this post on Decisions & Dragons I answer "Should we abandon RL?"
The answer is obviously no, but people ask because they have a fundamental misunderstanding of what RL is.
RL is a problem, not an approach.
www.decisionsanddragons.com/posts/should...