Research map / Bandits and online learning / Online convex optimization and games
A Regret Minimization Approach to Iterative Learning Control
Read the paperCheck your idea against 108,967 papers
AI-extracted summary. Written by AI from the paper's title only (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 changed | Where | Measured | Effect |
|---|---|---|---|
| Replace ILC policy update with iGPC (gradient perturbation controller with open-loop plan update) | iterative learning control on linear and non-linear systems · Double Integrator, Quadrotor, Reacher | rollouts needed to reach loss / terminal cost | Helped |
| Use gradient perturbation (disturbance-action feedback) controller with rollout-adaptive feedback versus ILC on sinusoidal time-varying perturbations with phase shifts | iGPC vs ILC on Double Integrator · Double Integrator sinusoidal perturbations | cost | Helped |
| Use gradient perturbation controller vs ILC with gradually increasing offsets | iGPC vs ILC on Double Integrator · Double Integrator gradually increasing offsets | cost | No clear effect |
| Use iGPC vs ILC with constant offsets | iGPC vs ILC on Double Integrator · Double Integrator constant offset | cost on first rollout | Helped |
Closest papers by meaning
- Online Control of Unknown Time-Varying Dynamical Systems (NeurIPS 2021 · similarity 0.90)
- Policy Optimization as Online Learning with Mediator Feedback (AAAI 2021 · similarity 0.88)
- Horizon-Free and Variance-Dependent Reinforcement Learning for Latent Markov Decision Processes (ICML 2023 · similarity 0.88)
- Regret-Free Reinforcement Learning for Temporal Logic Specifications (ICML 2025 · similarity 0.88)
- Policy-Regret Minimization in Markov Games with Function Approximation (ICML 2025 · similarity 0.88)
- Efficient Exploration in Average-Reward Constrained Reinforcement Learning: Achieving Near-Optimal Regret With Posterior Sampling (ICML 2024 · similarity 0.88)
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.