AI Paper Atlas

Research map / Reinforcement learning / Visual and representation RL

Neural optimal feedback control with local learning rules

Johannes Friedrich, Siavash Golkar, Shiva Farashahi, Alexander Genkin, Anirvan M. Sengupta, Dmitri Chklovskii

NeurIPS 2021 · Reinforcement learning › Visual and representation RL · approach: Inferring decision-making from behavior · 5 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 an internal state model to predict through delayed sensory feedbackBio-OFC on double-integrator control · Double integrator, LDS1 and LDS2, across sensory delayscontrol costImproved
Learn the controller from delayed observations without an internal state modelModel-free policy gradient · Double integrator, LDS1 and LDS2, across sensory delayscontrol costHurt
Adapt the Kalman gain online as observation noise changesBio-OFC · Double integrator, LDS1 with changing observation noiseprediction MSEImproved
Learn the system matrices and filter jointly onlineBio-OFC · Double integrator, LDS1 and LDS2prediction MSEImproved
Learn the controller while identifying the system in closed loopBio-OFC · Double integrator, LDS1 and LDS2control costImproved
Use local learning rules by replacing Cᵀ with L (ablation)Bio-OFC adaptive filter · Double integrator, LDS1 with changing observation noiseprediction MSENo clear effect
Over-represent the latent state as 3-dimensional rather than 2-dimensional (ablation)Bio-OFC · Double integrator, LDS2prediction MSENo clear effect
Keep controller weights fixed and adapt only the estimator (ablation)Bio-OFC · Reaching movements, force-field adaptationtrajectory match to human behaviorNo clear effect
Use signal-dependent motor noise instead of additive noise (ablation)Bio-OFC · Reaching movements, force-field adaptationtrajectory match to human behaviorNo clear effect
Initialize the alignment eigenvalue at or below zero (ablation)Bio-OFC adaptive filter · Double integrator, LDS1asymptotic prediction MSEHurt
Replace the internal state estimator with direct policy-gradient control from delayed observationsGym-Fly agent · Gym-Flytarget overshootHurt

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