AI ALIGNMENT FORUM
AF

peligrietzer
Ω49200
Message
Dialogue
Subscribe

Posts

Sorted by New

Wikitag Contributions

Comments

Sorted by
Newest
0peligrietzer's Shortform
3y
0
No wikitag contributions to display.
Behavioural statistics for a maze-solving agent
peligrietzer2y10

I'd maybe point the finger more at the simplicity of the training task than at the size of the network? I'm not sure there's strong reason to believe the network is underparameterized for the training task. But I agree that drawing lessons from small-ish networks trained on simple tasks requires caution. 

Reply
22The Problem With the Word ‘Alignment’
1y
2
38Paper: Understanding and Controlling a Maze-Solving Policy Network
2y
0
22Behavioural statistics for a maze-solving agent
2y
10
37Maze-solving agents: Add a top-right vector, make the agent go to the top-right
2y
7
140Understanding and controlling a maze-solving policy network
2y
23
47Predictions for shard theory mechanistic interpretability results
2y
6
11[Simulators seminar sequence] #2 Semiotic physics - revamped
2y
14
19 [Simulators seminar sequence] #1 Background & shared assumptions
3y
3
27A Short Dialogue on the Meaning of Reward Functions
3y
0