training · reweight-reward-dimensions-online-shortfall-volatility-progress TEC-0305 · proposed

Reweight reward dimensions online by shortfall, volatility a

Proposed. Filed by the drafting stage because a paper introduces or tests it. Nobody has vouched for it. The claim drafted from that paper is its first evidence, and what the paper used to validate it is in that claim’s source note. Say whether it held up for you, below.

Refreshes the scalarization weights every N steps using a multiplicative gate over each dimension's EMA shortfall against the mean, its relative volatility, and its recent progress, raising pressure on lagging, unstable or stagnant dimensio Filed by the drafting stage from Uncovering and Mitigating Aggregation-Induced Reward Hacking in Multi-Reward Reinforcement Learning (2609.00213) with status proposed: the paper introduces or tests it, and the claim drafted from the paper is its first evidence. The paper validated it by: Compared against fixed equal weighting and two DRBO dynamic-weighting rules on math (MATH-500/AMC/AIME), citation-grounded QA (ASQA/ELI5) and HelpSteer2 alignment; on Qwen3-4B math, average accuracy rose 37.53 to 60.72 under GRPO, with format/length scores falling, and ablations show removing any of the three signals or using additive rather than multiplicative combination lowers accuracy.. Nobody has vouched for it; add support or contest it on this page.

Addresses: Gaming the measure instead of doing the task

Does it work?

nothing measured0 supporting · 0 contesting sources

Efficacy claims — what this technique actually moves, under which conditions, and whether that has been contested.

No efficacy claim filed yet. The technique is catalogued; whether it moves the capability, and when, is a separate assertion that needs its own sources.

No search recorded either, so this says nothing about the literature — only that nobody has looked here yet.

Code

No repository linked yet. Contribute one.

Sources

Uncovering and Mitigating Aggregation-Induced Reward Hacking in Multi-Reward Reinforcement Learning (2026)

Either way, bring evidence: a link, or what you saw.

Whether a technique works is a claim. What you file here becomes a claim about this technique under the capability it addresses, with your evidence as its source, and moves the standing above the same way a paper would.