AI ethics evidence index Search
Source-linked daily record
Evidence record 4340 · automatically gathered

ROAD: Adaptive Data Mixing for Offline-to-Online Reinforcement Learning via Bi-Level Optimization

Offline-to-online reinforcement learning harnesses the stability of offline pretraining and the flexibility of online fine-tuning. A key challenge lies in the non-stationary distribution shift between offline datasets and the evolving online policy. Common approaches often rely on static mixing ratios or heuristic-based replay strategies, which lack adaptability to different environments and varying training dynamics, resulting in suboptimal tradeoff between stability and asymptotic performance.

Record details

Published: 14 May 2026
Source: arXiv
Category: Research
Topics: Regulation · Environment
Retrieved: 14 July 2026

source-onlyevidence status

These records share source-supplied organisations, an exact publisher byline, automatic topics or regions. The reason is shown on every link; related does not mean supporting, agreeing with or verifying this record.

Shared topic: Regulation · Shared topic: Environment

GAGPO: Generalized Advantage Grouped Policy Optimization

arXiv · 13 May 2026

Shared topic: Regulation · Shared topic: Environment

Bridging Domain Gaps with Target-Aligned Generation for Offline Reinforcement Learning

arXiv · 13 May 2026

Shared topic: Regulation · Shared topic: Environment

LLM-X: A Scalable Negotiation-Oriented Exchange for Communication Among Personal LLM Agents

arXiv · 12 May 2026

Shared topic: Regulation · Shared topic: Environment

When Does Non-Uniform Replay Matter in Reinforcement Learning?

arXiv · 11 May 2026

Shared topic: Regulation · Shared topic: Environment

Jurisdiction over Ubiquitous Copyright Infringements: Should Right-Holders Be Allowed to Sue at Home?

arXiv · 17 May 2026

Shared topic: Regulation · Shared topic: Environment

SkillsVote: Lifecycle Governance of Agent Skills from Collection, Recommendation to Evolution

arXiv · 18 May 2026

How to cite this record

ethics.ai (14 May 2026), “ROAD: Adaptive Data Mixing for Offline-to-Online Reinforcement Learning via Bi-Level Optimization,” evidence record 4340, https://ethics.ai/record/4340 (originally published by arXiv).

JSON

Use and limitations

This page is a stable index and citation surface for a source record. ethics.ai did not author the underlying report and has not independently verified every claim. Automatic topics may be imperfect. For consequential use, quote and cite the original publisher.