---
title: "CRONOS: Benchmarking Non-Episodic Reinforcement Learning for Robotic Manipulation"
source: "arXiv AI/CL/LG（论文）"
source_tier: "t2"
url: "https://arxiv.org/abs/2611.05080v1"
permalink: "https://feed.astralor.com/items/itm_b5570212d8525bac383becc3"
published: "2026-11-03T15:41:07.000Z"
score: 58
channel: "tech"
tags: ["RAG","多模态","CRONOS","Benchmarking Non-Episodic Reinforcement","Learning","Robotic Manipulation Reinforcement","However","Reinforcement"]
---

# CRONOS: Benchmarking Non-Episodic Reinforcement Learning for Robotic Manipulation

## At a glance

Reinforcement learning (RL) is promising for adapting robot policies to unstructured real-world environments. However, standard RL pipelines rely on episodic training with frequent scene resets, which is impractical for…

## Key points

- Reinforcement learning (RL) is promising for adapting robot policies to unstructured real-world environments.
- However, standard RL pipelines rely on episodic training with frequent scene resets, which is impractical for real-world deployment due to the need for substantial human intervention.
- While prior work has studied non-episodic RL in relatively small policies trained from scratch, its behavior when fine-tuning modern large-scale pre-trained vision-language-action (VLA) models remains underexplored.

## Full text

Reinforcement learning (RL) is promising for adapting robot policies to unstructured real-world environments. However, standard RL pipelines rely on episodic training with frequent scene resets, which is impractical for real-world deployment due to the need for substantial human intervention. While prior work has studied non-episodic RL in relatively small policies trained from scratch, its behavior when fine-tuning modern large-scale pre-trained vision-language-action (VLA) models remains underexplored. In this work, we introduce CRONOS, a simulation benchmark for RL fine-tuning of VLAs under non-episodic scene resets. CRONOS leverages high-fidelity physics simulators and adopts shared-scene multi-task settings. Using CRONOS, we show that naively fine-tuning pre-trained policies fails in non-episodic settings due to shifts in object configurations and end-effector poses; however, these challenges can be mitigated through targeted reset allocation and by addressing biases in pre-trained models. Moreover, we find that non-episodic training enhances long-horizon manipulation and improves generalization to previously unseen object configurations and task sequences. Project page: https://embodiedai-ntu.github.io/cronos/

---

Verify against the original before citing; curated by Astral Feed: https://feed.astralor.com/items/itm_b5570212d8525bac383becc3