mlsanityData to 14 Oct 2026

Flowing Through States: Neural ODE Regularization for Reinforcement Learning

arXiv 2608.06595 ↗First posted 6 Aug 2026cs.LG cs.AIcited by 0

On the map: Deep reinforcement learning methods → Deep RL algorithms and representations

Abstract (arXiv)

Neural networks applied to sequential decision-making tasks typically rely on latent representations of environment states. While environment dynamics dictate how semantic states evolve, the corresponding latent transitions are usually left implicit, creating a potential misalignment between the two. We propose to model latent dynamics explicitly by drawing an analogy between Markov decision process (MDP) trajectories and ordinary differential equation (ODE) flows: in both cases, the current state fully determines its successors. Building on this view, we introduce a neural ODE-based regularization method that enforces latent embeddings to follow consistent ODE flows, thereby aligning representation learning with environment dynamics. Although broadly applicable to deep learning agents, we demonstrate its effectiveness in reinforcement learning by integrating it into Actor-Critic algorithms. Our approach yields major performance gains across various standard Atari benchmarks for A2C and gridworld environments for PPO.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Placed in Deep RL algorithms and representations, one of 15 directions in Deep reinforcement learning methods. Builds on 19 of its 29 references that are in the map. First posted on arXiv 6 Aug 2026.

Builds on

19 of 29 references.

References · 19

  1. 2015Deep Residual Learning for Image Recognitioncited by 52,096
  2. 2017Proximal Policy Optimization Algorithmscited by 15,215
  3. 2018Soft Actor-Critic: Off-Policy Maximum Entropy Deep Reinforcement Learning with a Stochastic Actorcited by 4,885
  4. 2018Neural Ordinary Differential Equationscited by 3,779
  5. 2013Playing Atari with Deep Reinforcement Learningcited by 3,274
  6. 2016Asynchronous Methods for Deep Reinforcement Learningcited by 2,258
  7. 2016An overview of gradient descent optimization algorithmscited by 1,033
  8. 2017Stable Architectures for Deep Neural Networkscited by 341
  9. 2023Minigrid & Miniworld: Modular & Customizable Reinforcement Learning Environments for Goal-Oriented Taskscited by 327
  10. 2020Data-Efficient Reinforcement Learning with Self-Predictive Representationscited by 318
  11. 2022On Neural Differential Equationscited by 268
  12. 2017Beyond Finite Layer Neural Networks: Bridging Deep Architectures and Numerical Differential Equationscited by 203
7 more
  1. 2019Neural Jump Stochastic Differential Equationscited by 150
  2. 2021Contrastive Behavioral Similarity Embeddings for Generalization in Reinforcement Learningcited by 123
  3. 2020Dreaming: Model-based Reinforcement Learning by Latent Imagination without Reconstructioncited by 66
  4. 2023TACO: Temporal Latent Action-Driven Contrastive Loss for Visual Reinforcement Learningcited by 57
  5. 2020Model-based Reinforcement Learning for Semi-Markov Decision Processes with Neural ODEscited by 32
  6. 2020DyNODE: Neural Ordinary Differential Equations for Dynamics Modeling in Continuous Controlcited by 18
  7. 2023Modulated Neural ODEscited by 10

Built on by

Not cited yet.

Similar, not cited

Close in wording, no citation either way

  1. 2026Neural ODE and SDE Models for Adaptation and Planning in Model-Based Reinforcement Learning
  2. 2026From Ticks to Flows: Dynamics of Neural Reinforcement Learning in Continuous Environments
  3. 2026Unifying Model-Free Efficiency and Model-Based Representations via Latent Dynamics
  4. 2024Towards Unraveling and Improving Generalization in World Models
  5. 2026A Survey of Flow Matching in Reinforcement Learning
  6. 2026Ada-Diffuser: Latent-Aware Adaptive Diffusion for Decision-Making
  7. 2025Normalizing Flows are Capable Models for Continuous Control
  8. 2026Explicit Critic Guidance for Aligning Diffusion Models