CRONOS: Benchmarking Non-Episodic Reinforcement Learning for Robotic Manipulation
Organizations: Department of Computer Science and Information Engineering, National Taiwan University, Taipei, Taiwan
Abstract
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/
Figures & tables
| Model | Overlap | Cluttered | |
| OpenVLA | 80 | 0.554 | 0.494 |
| 320 | 0.593 | 0.536 | |
| SpatialVLA | 80 | 0.552 | 0.512 |
| 320 | 0.643 | 0.550 |
Appendix figures & tables2 assets
Supplementary material from the paper’s appendix.
Appendix
| Hyperparameter | Value |
| PPO | |
| PPO epochs per update | 1 |
| Clip ratio ( ) | 0.2 |
| Discount factor ( ) | 0.99 |
| GAE parameter ( ) | 0.95 |
| Entropy coefficient | 0.0 |
Robotic RL
Robotic reinforcement learning uses trial-and-error learning to help robots control, navigate, and manipulate objects.
See all 329 papers