---
title: "RIDGE: State-Conditioned Reward Blending for Behavioral Coverage in Deep RL Game Agents"
source: "arXiv AI/CL/LG（论文）"
source_tier: "t2"
url: "https://arxiv.org/abs/2611.05601v1"
permalink: "https://feed.astralor.com/items/itm_720dcbaee2893c1cc5ceff24"
published: "2026-11-03T20:41:36.000Z"
score: 56
channel: "ai"
tags: ["AI Agent","RAG","RIDGE","State-Conditioned Reward Blending","Behavioral Coverage","Deep","Game Agents","Explorer"]
---

# RIDGE: State-Conditioned Reward Blending for Behavioral Coverage in Deep RL Game Agents

## 速览

A deep RL agent trained on a fixed persona reward plays one way: an Explorer keeps exploring while starving, a Survivor hoards on an empty map. Since each persona fixes its own reward, automated playtesting trains N age…

## 关键点

- A deep RL agent trained on a fixed persona reward plays one way: an Explorer keeps exploring while starving, a Survivor hoards on an empty map.
- Since each persona fixes its own reward, automated playtesting trains N agents for N styles.
- Changing reward composition mid-episode runs into the switching-stability dilemma: PPO degrades under non-stationary rewards.

## 全文

A deep RL agent trained on a fixed persona reward plays one way: an Explorer keeps exploring while starving, a Survivor hoards on an empty map. Since each persona fixes its own reward, automated playtesting trains N agents for N styles. Changing reward composition mid-episode runs into the switching-stability dilemma: PPO degrades under non-stationary rewards. We present RIDGE, a single-agent architecture that sidesteps the dilemma with two design choices: a state-conditioned blender that computes softmax-normalized sigmoid weights from slow-moving state variables, and a multi-head critic that trains one value head per persona on its own stationary signal. On Crafter with four personas, one \ridge agent acquires both branches of the wood-tier crafting/combat split that no fixed-persona baseline solves jointly, and a sharpness ablation confirms state-conditioning drives the gain. We position these results as demonstrations of the blending mechanism's dynamics across n=3 seeds per condition; larger multi-seed sweeps remain future work.

---

引用前请核对原文;本文由星际流动整理:https://feed.astralor.com/items/itm_720dcbaee2893c1cc5ceff24