AI Paper Atlas

Research map / Reinforcement learning / Policy gradient and actor-critic

Integral Performance Approximation for Continuous-Time Reinforcement Learning Control

Brent A. Wallace, Jennie Si

ICLR 2025 · Reinforcement learning › Policy gradient and actor-critic · approach: Model-based RL with guarantees

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

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