Jianxin Bi — accepted AI-conference papers

2025

Imitation Learning with Limited Actions via Diffusion Planners and Deep Koopman Controllers

Jianxin Bi, Kelvin Lim, Kaiqi Chen, Yifei Huang, Harold Soh

ICRA 2025

Recent advances in diffusion-based robot policies have demonstrated significant potential in imitating multi-modal behaviors. However, these approaches typically require large quantities of demonstration data paired with corresponding robot action labels, creating a substantial data collection burde

Cited by 4 Source ↗code ↗Scholar ↗

2023

Safety-Constrained Policy Transfer with Successor Features

Zeyu Feng, Bowen Zhang, Jianxin Bi, Harold Soh

ICRA 2023poster

In this work, we focus on the problem of safe policy transfer in reinforcement learning: we seek to leverage existing policies when learning a new task with specified constraints. This problem is important for safety-critical applications where interactions are costly and unconstrained exploration c…

Cited by 7 Source ↗code ↗Scholar ↗