{
  "id": 17944,
  "url": "https://arxiv.org/abs/2608.06595v1",
  "title": "Flowing Through States: Neural ODE Regularization for Reinforcement Learning",
  "summary": "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 sta",
  "authors": "Mohamed Ghanem, Bernd Finkbeiner",
  "category": "research",
  "topics": "safety-alignment,environment",
  "orgs": null,
  "regions": null,
  "published_at": "2026-08-06T21:11:16.000Z",
  "fetched_at": "2026-08-10T05:10:00.488Z",
  "source_slug": "arxiv-cslg",
  "source_name": "arXiv cs.LG",
  "source_homepage": "https://arxiv.org/list/cs.LG/recent",
  "ethics_ai_record_url": "https://ethics.ai/record/17944",
  "original_url": "https://arxiv.org/abs/2608.06595v1",
  "evidence_status": "source-only",
  "attribution": "via ethics.ai"
}