Publications

Conference Papers

A Forget‑and‑Grow Strategy for Deep Reinforcement Learning Scaling in Continuous Control

Published in ICML, 2025

Propose FoG, a novel deep RL algorithm that integrates experience replay decay and network expansion; accepted as ICML 2025 poster.

Recommended citation: Kang, Z., Hu, C., Luo, Y., Yuan, Z., Zheng, R., & Xu, H. (2025). "A Forget‑and‑Grow Strategy for Deep Reinforcement Learning Scaling in Continuous Control." International Conference on Machine Learning (ICML).
Download Paper

3D Diffusion Policy: Generalizable Visuomotor Policy Learning via Simple 3D Representations

Published in RSS, 2024

Introduce DP3, integrating 3D visual representations into diffusion policies for generalizable visuomotor learning.

Recommended citation: Ze, Y., Zhang, G., Zhang, K., Hu, C., Wang, M., & Xu, H. (2024). "3D Diffusion Policy: Generalizable Visuomotor Policy Learning via Simple 3D Representations." Robotics: Science and Systems (RSS).
Download Paper

Chenyuan Hu

Publications

Conference Papers

A Forget‑and‑Grow Strategy for Deep Reinforcement Learning Scaling in Continuous Control

3D Diffusion Policy: Generalizable Visuomotor Policy Learning via Simple 3D Representations