Prover-estimator debate replaces the opponent's choice of subclaim with probability estimates, and the paper claims this avoids obfuscation, though the proof of the core indistinguishability lemma is flawed.
Playing Large Games with Oracles and AI Debate
1 Pith paper cite this work. Polarity classification is still indexing.
abstract
We consider regret minimization in repeated games with a very large number of actions. Such games are inherent in the setting of AI Safety via Debate \cite{irving2018ai}, and more generally games whose actions are language-based. Existing algorithms for online game playing require per-iteration computation polynomial in the number of actions, which can be prohibitive for large games. We thus consider oracle-based algorithms, as oracles naturally model access to AI agents. With oracle access, we characterize when internal and external regret can be minimized efficiently. We give a novel efficient algorithm for simultaneous external and internal regret minimization whose regret depends logarithmically on the number of actions. We conclude with experiments in the setting of AI Safety via Debate that shows the benefit of insights from our algorithmic analysis.
fields
cs.AI 1years
2025 1verdicts
REJECT 1representative citing papers
citing papers explorer
-
Avoiding Obfuscation with Prover-Estimator Debate
Prover-estimator debate replaces the opponent's choice of subclaim with probability estimates, and the paper claims this avoids obfuscation, though the proof of the core indistinguishability lemma is flawed.