mlsanityData to 14 Oct 2026

Optimal control of the future via prospective learning with control

arXiv 2511.08717 ↗First posted 11 Nov 2025stat.ML cs.LGcited by 0

Not on the map. Why?

Abstract (arXiv)

Optimal control of the future is the next frontier for AI. Current approaches to this problem are typically rooted in reinforcement learning (RL). RL is mathematically distinct from supervised learning, which has been the main workhorse for the recent achievements in AI. Moreover, RL typically operates in a stationary environment with episodic resets, limiting its utility. Here, we extend supervised learning to address learning to control in non-stationary, reset-free environments. Using this framework, called ''Prospective Learning with Control'' (PLuC), we prove that under certain fairly general assumptions, empirical risk minimization (ERM) asymptotically achieves the Bayes optimal policy. We then consider a specific instance of prospective learning with control: foraging, a canonical task relevant to both natural and artificial agents. We illustrate that modern RL algorithms, which assume stationarity, struggle in these non-stationary reset-free environments. Even with time-aware modifications, they converge orders of magnitude slower than our prospective foraging agents on a simple 1-D foraging benchmark. Code is available at: https://github.com/neurodata/procontrol.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Builds on 14 of its 38 references that are in the map. First posted on arXiv 11 Nov 2025.

Builds on

14 of 38 references.

References · 14

  1. 2017Attention Is All You Needcited by 60,361
  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. 2018Soft Actor-Critic Algorithms and Applicationscited by 1,240
  5. 2017Mastering Chess and Shogi by Self-Play with a General Reinforcement Learning Algorithmcited by 734
  6. 2020Towards Continual Reinforcement Learning: A Review and Perspectivescited by 274
  7. 2023A Definition of Continual Reinforcement Learningcited by 101
  8. 2017Boltzmann Exploration Done Rightcited by 69
  9. 2020Reset-Free Lifelong Learning with Skill-Space Planningcited by 38
  10. 2023Continual Learning as Computationally Constrained Reinforcement Learningcited by 37
  11. 2022You Only Live Once: Single-Life Reinforcement Learningcited by 24
  12. 2020Simple Lifelong Learning Machinescited by 9
2 more
  1. 2024Prospective Learning: Learning for a Dynamic Futurecited by 4
  2. 2025Prospective Learning in Retrospectcited by 1

Built on by

Not cited yet.

Similar, not cited

Close in wording, no citation either way

  1. 2022Dichotomy of Control: Separating What You Can Control from What You Cannot
  2. 2025An Optimal Policy for Learning Controllable Dynamics by Exploration
  3. 2021Policy Gradients Incorporating the Future
  4. 2024MetaCURL: Non-stationary Concave Utility Reinforcement Learning
  5. 2025Reinforcement Learning with Random Time Horizons
  6. 2026Learning from the Near Future: Temporal Self-Distillation for RLVR
  7. 2026Safe Exploration via Policy Priors
  8. 2024Decision Making in Non-Stationary Environments with Policy-Augmented Search