AI Paper Atlas

Research map / Reinforcement learning / MDPs and planning

Flowing Through States: Neural ODE Regularization for Reinforcement Learning

Mohamed Ghanem, Bernd Finkbeiner

ICLR 2026 · Reinforcement learning › MDPs and planning · approach: Average-reward and regularized MDPs · 0 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
add FlowReg (Index sampling) to A2CA2C · Atari Qbertmean episode reward: 4374.30 -> 8306.05Improved
add FlowReg (Index sampling) to A2CA2C · Atari Riverraidmean episode reward: 1862.27 -> 2946.34Improved
add FlowReg (Exp-Decay sampling) to A2CA2C · Atari BeamRidermean episode reward: 960.66 -> 1593.11Improved
use Index instead of Exp-Decay time sampling (ablation)FlowReg · Atari Qbertmean episode reward: 8306.05 vs 6903.15Mixed
apply FlowReg every 10 updates instead of every 5 (Exp-Decay) (ablation)FlowReg · Atari Qbert (Exp-Decay)mean episode reward: 5286.60 -> 6903.15Improved
apply FlowReg every 5 updates instead of every 10 (Index) (ablation)FlowReg · Atari Qbert (Index)mean episode reward: 6569.51 -> 8306.05Improved
lower FlowReg frequency to once every 20 updates (ablation)FlowReg · Atari Qbertmean episode reward: 4374.30 -> 5985.70No clear effect
add FlowReg to A2C smoothness of latent pathsA2C · Atari Qbertlatent path length (normalized): 34.39 -> 4.20Improved
add FlowReg to A2C acceleration energyA2C · Atari Breakoutacceleration energy (normalized): 31432.59 -> 94.98Improved
replace TACO with FlowRegA2C · Atari Breakoutmean episode reward: 11.12 -> 24.03Improved
add TACO to A2CA2C · Atari Qbertmean episode reward: 4374.30 -> 2434.05Hurt
add FlowReg to PPOPPO · Minigrid FourRooms and Dynamic-Obstaclesepisode rewardImproved

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