Safe Pontryagin Differentiable Programming
Dec 6, 2021
Speakers
Wanxin Jin
Speaker · 0 followers
Shaoshuai Mou
Speaker · 0 followers
George Pappas
Speaker · 0 followers
About
We propose a Safe Pontryagin Differentiable Programming (Safe PDP) methodology, which establishes a theoretical and algorithmic safe differentiable framework to solve a broad class of safety-critical learning and control tasks—problems that require the guarantee of both immediate and long-term constraint satisfaction at any stage of the learning and control progress. In the spirit of interior-point methods, Safe PDP handles different types of state and input constraints by incorporating them into the cost and loss through barrier functions. We prove the following fundamental features of Safe PDP: first, both the constrained solution and its gradient in backward pass can be approximated by solving a more efficient unconstrained counterpart; second, the approximation for both the solution and its gradient can be controlled for arbitrary accuracy using a barrier parameter; and third, importantly, any intermediate results throughout the approximation and optimization are strictly respecting all constraints, thus guaranteeing safety throughout the entire learning and control process. We demonstrate the capabilities of Safe PDP in solving various safe learning and control tasks, including safe policy optimization, safe motion planning, and learning MPCs from demonstrations, on different challenging control systems such as 6-DoF maneuvering quadrotor and 6-DoF rocket powered landing.We propose a Safe Pontryagin Differentiable Programming (Safe PDP) methodology, which establishes a theoretical and algorithmic safe differentiable framework to solve a broad class of safety-critical learning and control tasks—problems that require the guarantee of both immediate and long-term constraint satisfaction at any stage of the learning and control progress. In the spirit of interior-point methods, Safe PDP handles different types of state and input constraints by incorporating them int…
Organizer
NeurIPS 2021
Account · 1.9k followers
About NeurIPS 2021
Neural Information Processing Systems (NeurIPS) is a multi-track machine learning and computational neuroscience conference that includes invited talks, demonstrations, symposia and oral and poster presentations of refereed papers. Following the conference, there are workshops which provide a less formal setting.
Like the format? Trust SlidesLive to capture your next event!
Professional recording and live streaming, delivered globally.
Sharing
Recommended Videos
Presentations on similar topic, category or speaker
Benchmarking Bias Mitigation Algorithms in Representation Learning through Fairness Metrics
Watch later
Charan Reddy, …
Total of 0 viewers voted for saving the presentation to eternal vault which is 0.0%
Learning Tree Interpretation from Object Representation for Deep Reinforcement Learning
Watch later
Guiliang Liu, …
Total of 0 viewers voted for saving the presentation to eternal vault which is 0.0%
Medical Dead-ends and Learning to Identify High-Risk States and Treatments
Watch later
Mehdi Fatemi, …
Total of 0 viewers voted for saving the presentation to eternal vault which is 0.0%
Accelerating Quadratic Programming with Reinforcement Learning
Watch later
Total of 0 viewers voted for saving the presentation to eternal vault which is 0.0%
Panel Discussion: “Machine Learning in Social Systems: Challenges and Opportunities from Program Evaluation”
Watch later
Total of 0 viewers voted for saving the presentation to eternal vault which is 0.0%
FFA-IR: Towards an Explainable and Reliable Medical Report Generation Benchmark
Watch later
Mingjie Li, …
Total of 0 viewers voted for saving the presentation to eternal vault which is 0.0%