LESSWRONG
LW

Karolis Jucys
22240
Message
Dialogue
Subscribe

PhD student in reinforcement learning and interpretability at University of Bath.

https://ka.rol.is/

Posts

Sorted by New

Wikitag Contributions

Comments

Sorted by
Newest
No wikitag contributions to display.
Jesse Hoogland's Shortform
Karolis Jucys7mo10

DreamerV3 is not a great example, as they use so many hacks to make the task easier that it barely counts as getting a diamond or Minecraft anymore. Action shaping, macro actions, instant block breaking, fake "bug fixing", all to get a diamond in 0.4% of episodes.

More info here: https://x.com/Karolis_Ram/status/1785750372394348632

Reply
How should TurnTrout handle his DeepMind equity situation?
Karolis Jucys2y10

Would "delta hedging" be useful here? It helps hedge long option exposure by shorting some amount of a stock.
For example, at the money calls generally have a delta of 0.5, so holding 100 at the money calls and shorting 50 shares makes you roughly neutral for small moves in the underlying asset.
Would probably require monthly rebalancing based on how many options you effectively hold and market moves. It also wouldn't work well if AGI happens at GDM and Google stock goes exponential ("volatility smile" problem).

Reply
DeepMind: Model evaluation for extreme risks
Karolis Jucys2y32

non pdf arxiv link: https://arxiv.org/abs/2305.15324

Reply
Polaris, Five-Second Versions, and Thought Lengths
Karolis Jucys3y20

For the four examples of
24-16=12, 53-25=25, 34-16=13, 63-17=16
is this the pattern?

ab-cd=ca

Reply
9Interpretability in Action: Exploratory Analysis of VPT, a Minecraft Agent
1y
0
16Colour versus Shape Goal Misgeneralization in Reinforcement Learning: A Case Study
2y
1