# CASOG: Conservative Actor-critic with SmOoth Gradient for Skill Learning in Robot-Assisted Intervention

arXiv: https://arxiv.org/abs/2304.09632 · HTML: https://mlsanity.com/paper/2304.09632/

## Key facts

- Cited by 6 papers in the map (data through 14 Oct 2026).
- Placed in Safe offline RL, one of 13 directions in Offline RL and imitation learning from data.
- First posted on arXiv 19 Apr 2023.

## Placed in

- Offline RL and imitation learning from data / [Safe offline RL](https://mlsanity.com/offlinerl/safe-offline-rl/)

## Built on by (most cited first, 6 of 6)

- [SPIRONet: Spatial-Frequency Learning and Graph-based Channel Interaction Network for Vessel Segmentation](https://mlsanity.com/paper/2406.19749/) (2024)
- [DOMAIN: MilDly COnservative Model-BAsed OfflINe Reinforcement Learning](https://mlsanity.com/paper/2309.08925/) (2023)
- [CROP: Conservative Reward for Model-based Offline Policy Optimization](https://mlsanity.com/paper/2310.17245/) (2023)
- [Advancing Embodied Intelligence in Robotic-Assisted Endovascular Procedures: A Systematic Review of AI Solutions](https://mlsanity.com/paper/2504.15327/) (2025)
- [Towards Next-Generation Healthcare: A Survey of Medical Embodied AI for Perception, Decision-Making, and Action](https://mlsanity.com/paper/2606.15647/) (2026)
- [VeCAS: Vessel-Focused Contrast-Free Angiogram Synthesis for Vascular Interventions](https://mlsanity.com/paper/2608.22828/) (2026)

## Abstract (arXiv)

Robot-assisted intervention has shown reduced radiation exposure to physicians and improved precision in clinical trials. However, existing vascular robotic systems follow master-slave control mode and entirely rely on manual commands. This paper proposes a novel offline reinforcement learning algorithm, Conservative Actor-critic with SmOoth Gradient (CASOG), to learn manipulation skills from human demonstrations on vascular robotic systems. The proposed algorithm conservatively estimates Q-function and smooths gradients of convolution layers to deal with distribution shift and overfitting issues. Furthermore, to focus on complex manipulations, transitions with larger temporal-difference error are sampled with higher probability. Comparative experiments in a pre-clinical environment demonstrate that CASOG can deliver guidewire to the target at a success rate of 94.00% and mean backward steps of 14.07, performing closer to humans and better than prior offline reinforcement learning methods. These results indicate that the proposed algorithm is promising to improve the autonomy of vascular robotic systems.