mlsanityData to 14 Oct 2026

Action-Driven Processes for Continuous-Time Control

arXiv 2510.26672 ↗First posted 30 Oct 2025stat.ML cs.LGcited by 0

On the map: Deep reinforcement learning methods → RL theory and sample complexity

Abstract (arXiv)

At the heart of reinforcement learning are actions -- decisions made in response to observations of the environment. Actions are equally fundamental in the modeling of stochastic processes, as they trigger discontinuous state transitions and enable the flow of information through large, complex systems. In this paper, we unify the perspectives of stochastic processes and reinforcement learning through action-driven processes, and illustrate their application to spiking neural networks. Leveraging ideas from control-as-inference, we show that minimizing the Kullback-Leibler divergence between a policy-driven true distribution and a reward-driven model distribution for a suitably defined action-driven process is equivalent to maximum entropy reinforcement learning.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Placed in RL theory and sample complexity, one of 15 directions in Deep reinforcement learning methods. Builds on 1 of its 15 references that are in the map. First posted on arXiv 30 Oct 2025.

Builds on

1 of 15 references.

References · 1

  1. 2018Reinforcement Learning and Control as Probabilistic Inference: Tutorial and Reviewcited by 482

Built on by

Not cited yet.

Similar, not cited

Close in wording, no citation either way

  1. 2026From Ticks to Flows: Dynamics of Neural Reinforcement Learning in Continuous Environments
  2. 2025Diffusion-Augmented Markov Decision Processes for Maximum Entropy Reinforcement Learning
  3. 2025Reinforcement Learning with Action-Triggered Observations
  4. 2026Learning to Solve Stochastic Controls with Unknown Drifts and Running Rewards: Theory, Algorithms and Convergence
  5. 2026Neural ODE and SDE Models for Adaptation and Planning in Model-Based Reinforcement Learning
  6. 2025Act to See, See to Act: Diffusion-Driven Perception-Action Interplay for Adaptive Policies
  7. 2025Learning to Control Dynamical Agents via Spiking Neural Networks and Metropolis-Hastings Sampling
  8. 2026Maximum-Entropy Exploration with Future State-Action Visitation Measures