This website requires javascript to properly function. Consider activating javascript to get access to all site functionality.
Effective Altruism Forum
EA Forum
Login
Sign up
sergeivolodin
-262 karma
Joined
Oct 2020
Zürich, Switzerland
scholar.google.com/citations?user=AsDOBXIAAAAJ&hl=en
Message
Get notified
Interests:
AI safety
Community
Bio
Participation
2
AI safety
had a health crisis
Getting back on track
Posts
1
Sorted by New
1
Defending against Adversarial Policies in Reinforcement Learning with Alternating Training
sergeivolodin
sergeivolodin
+ 0 more
·
3y
ago
· 16m read
0
0
Comments
47
Topic contributions
3
