AI Paper Atlas

Research map / Reinforcement learning / Visual and representation RL

Pontryagin Differentiable Programming: An End-to-End Learning and Control Framework

Wanxin Jin, Zhaoran Wang, Zhuoran Yang, Shaoshuai Mou

NeurIPS 2020 · Reinforcement learning › Visual and representation RL · approach: Skill learning and diffusion policies · 10 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
Use PDP instead of policy cloning or inverse KKTImitation learning · Imitation learning environmentstraining lossImproved
Use PDP instead of policy cloning or inverse KKTImitation learning · Imitation learning environmentsconvergence speedImproved
Learn the control objective with PDPRobot arm imitation learning · Robot armimitation lossImproved
Use PDP instead of a neural-network dynamics model or DMDcSystem identification · Cart-pole, robot arm, and quadrotortraining lossImproved
Use PDP instead of a neural-network dynamics model or DMDcSystem identification · Cart-pole, robot arm, and quadrotorconvergence speedImproved
Use PDP instead of Adam to train the neural dynamics modelRobot arm neural dynamics learning · Robot armtraining lossImproved
Use PDP instead of Adam to train the neural dynamics modelRobot arm neural dynamics learning · Robot armlearning speedImproved
Use PDP instead of guided policy searchFeedback control · Cart-pole and robot armcontrol lossImproved
Optimize a polynomial policy with PDP instead of using iLQRQuadrotor planning · Quadrotorcontrol lossMixed
Increase polynomial policy degree from N=5 to N=35 (ablation)PDP polynomial policy · Quadrotor planningcontrol lossImproved
Use PDP rather than iLQRQuadrotor planning · Quadrotorconvergence speedHurt
Use PDP rather than iLQRQuadrotor planning · QuadrotorruntimeImproved

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy