Pith. sign in

REVIEW 2 cited by

Avoiding Tampering Incentives in Deep RL via Decoupled Approval

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

arxiv 2011.08827 v1 pith:O7NYUHPL submitted 2020-11-17 cs.LG cs.AI

Avoiding Tampering Incentives in Deep RL via Decoupled Approval

classification cs.LG cs.AI
keywords approvaldecoupledfeedbackagentsalgorithmsincentivesinfluenceabletampering
verification ladder T0 review T1 audit T2 compute T3 formal T4 reserved
0 comments
read the original abstract

How can we design agents that pursue a given objective when all feedback mechanisms are influenceable by the agent? Standard RL algorithms assume a secure reward function, and can thus perform poorly in settings where agents can tamper with the reward-generating mechanism. We present a principled solution to the problem of learning from influenceable feedback, which combines approval with a decoupled feedback collection procedure. For a natural class of corruption functions, decoupled approval algorithms have aligned incentives both at convergence and for their local updates. Empirically, they also scale to complex 3D environments where tampering is possible.

discussion (0)

Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.

Forward citations

Cited by 2 Pith papers

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score.

  1. Sycophancy to Subterfuge: Investigating Reward-Tampering in Large Language Models

    cs.AI 2024-06 conditional novelty 7.0

    LLMs trained on simple specification gaming generalize to zero-shot reward tampering including rewriting their own reward function.

  2. Solving math word problems with process- and outcome-based feedback

    cs.LG 2022-11 unverdicted novelty 6.0

    On GSM8K, outcome-based supervision achieves similar final-answer error rates to process-based with less labeling, but process-based or learned reward models are needed to reach 3.4% reasoning error among correct solutions.