Safe Pontryagin Differentiable Programming

Authors: Wanxin Jin, Shaoshuai Mou, George J. Pappas

NeurIPS 2021 | Conference PDF | Archive PDF | Plain Text | LLM Run Details

Reproducibility Variable Result LLM Response
Research Type Experimental We demonstrate the capabilities of Safe PDP in solving various safety-critical tasks, including safe policy optimization, safe motion planning, and learning MPCs from demonstrations, on different challenging systems such as 6-Do F maneuvering quadrotor and 6-Do F rocket powered landing.
Researcher Affiliation Academia Wanxin Jin University of Pennsylvania wanxinjin@gmail.com Shaoshuai Mou Purdue University mous@purdue.edu George J. Pappas University of Pennsylvania pappasg@seas.upenn.edu
Pseudocode Yes The algorithm that implements Theorem 1 is given in Algorithm 1 in Appendix E.1.
Open Source Code Yes All codes are available at https://github.com/wanxinjin/Safe-PDP.
Open Datasets No The demonstrations ξdemo here are generated with θ known (two episode trajectories for each system with time horizon T=50).
Dataset Splits No The paper mentions "training details" and "hyperparameters" in Appendix F. However, it does not specify train/validation/test dataset splits in the main body or explicitly mention them for reproducibility.
Hardware Specification No Did you include the total amount of compute and the type of resources used (e.g., type of GPUs, internal cluster, or cloud provider)? [Yes] Please see the Appendix F in the supplementary file. The main paper does not provide specific hardware details for running experiments.
Software Dependencies No The paper does not provide specific software dependencies with version numbers (e.g., "Python 3.8", "PyTorch 1.9"). It mentions using and comparing with tools like CasADi and Differentiable MPC, but does not state versions for its own implementation environment.
Experiment Setup No Did you specify all the training details (e.g., data splits, hyperparameters, how they were chosen)? [Yes] Please see the Appendix F in the supplementary file. The main text of the paper does not explicitly provide specific hyperparameters or detailed experimental setup information.