Pith. sign in

Playing Large Games with Oracles and AI Debate

1 Pith paper cite this work. Polarity classification is still indexing.

1 Pith paper citing it
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 1

years

2025 1

verdicts

REJECT 1

representative citing papers

Avoiding Obfuscation with Prover-Estimator Debate

cs.AI · 2025-06-16 · reject · novelty 8.0

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.

citing papers explorer

Showing 1 of 1 citing paper.

  • Avoiding Obfuscation with Prover-Estimator Debate cs.AI · 2025-06-16 · reject · none · ref 9 · internal anchor

    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.