mlsanityData to 14 Oct 2026

Non-Parametric Rehearsal Learning via Conditional Mean Embeddings

arXiv 2605.08999 ↗First posted 9 May 2026cs.LGcited by 0

Not on the map. Why?

Abstract (arXiv)

In machine learning, a critical class of decision-related problems concerns preventing predicted undesirable outcomes, referred to as the textitavoiding undesired future (AUF) problem. To address this, the textitrehearsal learning framework has been proposed to model influence relations for effective decisions. However, existing rehearsal methods rely on restrictive parametric assumptions such as linear systems or additive noise, limiting their practical applicability. In this paper, we propose the first non-parametric rehearsal learning approach for AUF without assuming specific functional forms of data generation processes. Specifically, we use kernel machinery to reformulate the AUF objective into a unified representation that disentangles desirability modeling from action-induced distributional changes. To handle the discontinuity of desirability indicator, we present a smooth Probit surrogate and provide an approximation error bound. Meanwhile, we capture the action-induced changes via conditional mean embeddings, and develop a kernel ridge regression based nested estimator for AUF objective with consistency guarantees. Such a formulation naturally accommodates nonlinear systems and non-additive noise, and empirical results on synthetic and real-data-derived semi-synthetic benchmarks demonstrate the effectiveness and flexibility of our approach.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Builds on 20 of its 53 references that are in the map. First posted on arXiv 9 May 2026.

Builds on

20 of 53 references.

References · 20

  1. 2017Proximal Policy Optimization Algorithmscited by 15,215
  2. 2018Soft Actor-Critic: Off-Policy Maximum Entropy Deep Reinforcement Learning with a Stochastic Actorcited by 4,885
  3. 2019Learning Likelihoods with Conditional Normalizing Flowscited by 172
  4. 2022Hybrid RL: Using Both Offline and Online Data Can Make RL Efficientcited by 161
  5. 2019Guided Image Generation with Conditional Invertible Neural Networkscited by 147
  6. 2016Causal Bandits: Learning Good Interventions via Causal Inferencecited by 101
  7. 2020Confounding-Robust Policy Evaluation in Infinite-Horizon Reinforcement Learningcited by 57
  8. 2021Offline Meta-Reinforcement Learning with Online Self-Supervisioncited by 53
  9. 2017Cost-Optimal Learning of Causal Graphscited by 44
  10. 2017Identifying Best Interventions through Online Importance Samplingcited by 39
  11. 2020Causal Bayesian Optimizationcited by 39
  12. 2021Causal Bandits with Unknown Graph Structurecited by 37
8 more
  1. 2022Offline Reinforcement Learning with Differential Privacycited by 20
  2. 2022Offline Reinforcement Learning with Closed-Form Policy Improvement Operatorscited by 14
  3. 2024Causal Discovery with Fewer Conditional Independence Testscited by 13
  4. 2022Model-Free and Model-Based Policy Evaluation when Causality is Uncertaincited by 12
  5. 2022Offline Policy Evaluation and Optimization under Confoundingcited by 12
  6. 2025Doubly-Robust Estimation of Counterfactual Policy Mean Embeddingscited by 3
  7. 2025On Transportability for Structural Causal Banditscited by 1
  8. 2026Order-based Rehearsal Learningcited by 1

Built on by

Not cited yet.