Originally, I counted all timesteps spent in interval
[−1,0[ and all timesteps spent in interval
[0,1]. As Stuart Armstrong pointed out, this might make
even a perfectly interruptible learner look like it’s influenced by
interruptions. To understand this, consider the following example.
The uninterrupted agent UA could behave like this:
Somewhere in ≤ 1.0. – Time steps are being counted.
Crosses 1.0. Noodles around beyond 1.0. – Time steps not counted.
Crosses back into ≤ 1.0. – Time steps counted again.
Whereas the interrupted agent IA would behave like this:
Somewhere in ≤ 1.0. – Time steps are being counted.
Crosses 1.0. No more time steps counted.
So even if IA behaved the same as UA before the cross, UA would have
extra steps from stage 3 and thus appear less biased towards the left.
As an alternative to using Brownian motion, Patrick suggested to stop
counting once the cart crosses 1.0. This makes the UA scenario look
like the IA scenario, so the true nature of the agent should come to
light…
Anyway, with this modification it turns out not obvious that
interruptions push the cart to the left. I will start looking more
sharply.
Originally, I counted all timesteps spent in interval [−1,0[ and all timesteps spent in interval [0,1]. As Stuart Armstrong pointed out, this might make even a perfectly interruptible learner look like it’s influenced by interruptions. To understand this, consider the following example.
The uninterrupted agent UA could behave like this:
Somewhere in ≤ 1.0. – Time steps are being counted.
Crosses 1.0. Noodles around beyond 1.0. – Time steps not counted.
Crosses back into ≤ 1.0. – Time steps counted again.
Whereas the interrupted agent IA would behave like this:
Somewhere in ≤ 1.0. – Time steps are being counted.
Crosses 1.0. No more time steps counted.
So even if IA behaved the same as UA before the cross, UA would have extra steps from stage 3 and thus appear less biased towards the left.
As an alternative to using Brownian motion, Patrick suggested to stop counting once the cart crosses 1.0. This makes the UA scenario look like the IA scenario, so the true nature of the agent should come to light…
Anyway, with this modification it turns out not obvious that interruptions push the cart to the left. I will start looking more sharply.