Research map / Reinforcement learning / Policy gradient and actor-critic
Integral Performance Approximation for Continuous-Time Reinforcement Learning Control
Brent A. Wallace, Jennie Si
Read the paperCheck your idea against 137,217 papers
AI-extracted summary. Written by AI from the paper's abstract only. Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Proposes integral performance approximation (IPA), a continuous-time RL control method that uses a partially known affine nonlinear dynamic model and state-action trajectory data with Kleinman-style structure for data-efficient optimal control.
Problem
Continuous-time reinforcement learning control that is data-efficient and robust when only partial knowledge of the physical environment dynamics is available.
Approach
Combines an affine nonlinear dynamic model that partially captures the physics with state-action trajectory data, using Kleinman algorithm structures to approximate integral performance and enable optimal control with fewer data requirements.
Experimental setup
Builds on: Kleinman algorithm
Closest papers by meaning
- Overcoming Slow Decision Frequencies in Continuous Control: Model-Based Sequence Reinforcement Learning for Model-Free Control (ICLR 2025 · similarity 0.85)
- EvoControl: Multi-Frequency Bi-Level Control for High-Frequency Continuous Control (ICML 2025 · similarity 0.84)
- Continuous Q-Score Matching: Diffusion Guided Reinforcement Learning for Continuous-Time Control (NeurIPS 2025 · similarity 0.84)
- Reinforcement Learning with Adaptive Regularization for Safe Control of Critical Systems (NeurIPS 2024 · similarity 0.84)
- Learning from Suboptimal Data in Continuous Control via Auto-Regressive Soft Q-Network (ICML 2025 · similarity 0.84)
- A Temporal Difference Method for Stochastic Continuous Dynamics (NeurIPS 2025 · similarity 0.84)
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.
