REVIEW 1 cited by
Virtuously Safe Reinforcement Learning
Not yet reviewed by Pith; the record is open.
This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.
SPECIMEN: schema-true, not a live event
T0 review · schema-true
One-sentence machine reading of the paper's core claim.
pith:XXXXXXXX · record.json · timestamp
Virtuously Safe Reinforcement Learning
read the original abstract
We show that when a third party, the adversary, steps into the two-party setting (agent and operator) of safely interruptible reinforcement learning, a trade-off has to be made between the probability of following the optimal policy in the limit, and the probability of escaping a dangerous situation created by the adversary. So far, the work on safely interruptible agents has assumed a perfect perception of the agent about its environment (no adversary), and therefore implicitly set the second probability to zero, by explicitly seeking a value of one for the first probability. We show that (1) agents can be made both interruptible and adversary-resilient, and (2) the interruptibility can be made safe in the sense that the agent itself will not seek to avoid it. We also solve the problem that arises when the agent does not go completely greedy, i.e. issues with safe exploration in the limit. Resilience to perturbed perception, safe exploration in the limit, and safe interruptibility are the three pillars of what we call \emph{virtuously safe reinforcement learning}.
Forward citations
Cited by 1 Pith paper
-
What if Pinocchio Were a Reinforcement Learning Agent: A Normative End-to-End Pipeline
The thesis presents Pino, an end-to-end pipeline that supervises reinforcement learning agents with argumentation-based normative advisors, introduces an algorithm for automatic argument extraction, and defines a miti...
discussion (0)
Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.