v0.4.0 released on 2025.04.21: Update reward functions for planning. Upload pretrained model for task planning. v0.3.0 released on 2025.04.16: Bugs fixed on environments registry, and tests had done ...
“Koopman-Inspired Proximal Policy Optimization (KIPPO)”. The goal of this implementation is to reproduce the main training structure and workflow described by the original authors using PyTorch for ...