---
title: "Transformer-Based Reinforcement Learning for Phase I Dose Allocation"
source: "arXiv AI/CL/LG（论文）"
source_tier: "t2"
url: "https://arxiv.org/abs/2611.00395v1"
permalink: "https://feed.astralor.com/items/itm_6e33123024e9d8b3429d295b"
published: "2026-10-30T21:22:44.000Z"
score: 54
channel: "tech"
tags: ["安全","Transformer-Based Reinforcement Learning","Phase","Dose Allocation Phase","Each","DLTs","Transformer"]
---

# Transformer-Based Reinforcement Learning for Phase I Dose Allocation

## At a glance

Phase I dose-finding trials must learn from sparse toxicity observations while limiting exposure to overly toxic doses. We develop a single reinforcement-learning policy for trials with different numbers of ordered dose…

## Key points

- Phase I dose-finding trials must learn from sparse toxicity observations while limiting exposure to overly toxic doses.
- We develop a single reinforcement-learning policy for trials with different numbers of ordered dose levels.
- Each dose is represented as a token containing its normalized position, accumulated patient count, observed dose-limiting toxicities (DLTs), and current-dose indicator.

## Full text

Phase I dose-finding trials must learn from sparse toxicity observations while limiting exposure to overly toxic doses. We develop a single reinforcement-learning policy for trials with different numbers of ordered dose levels. Each dose is represented as a token containing its normalized position, accumulated patient count, observed dose-limiting toxicities (DLTs), and current-dose indicator. A Transformer encoder summarizes the dose tokens, trial-conditioned cross-attention produces a fixed-dimensional trial representation, and a three-action policy chooses de-escalation, staying, or escalation. The final maximum tolerated dose (MTD) decision is deliberately kept outside the learned policy: after the planned sample size, weighted isotonic regression and a prespecified safety cap select the dose closest to the target toxicity probability. In the simulations, toxicity-penalized policies reduce DLT burden while unpenalized policies improve selection accuracy at the cost of greater toxicity. These results demonstrate a controllable safety--accuracy trade-off but do not establish superiority over conventional dose-finding designs.

---

Verify against the original before citing; curated by Astral Feed: https://feed.astralor.com/items/itm_6e33123024e9d8b3429d295b