mlsanityData to 14 Oct 2026

Decoupled Behavioral Cloning for Scalable Inductive Generalization in RL from Specifications

arXiv 2606.00838 ↗First posted 30 May 2026cs.AIcited by 0

On the map: Offline RL and imitation learning from data → Imitation learning methods

also in 1 more
Abstract (arXiv)

Inductive generalization is a framework for reinforcement learning (RL) generalization in which inductively related task instances admit inductively related policies. Prior work captures this structure via a higher-order policy-evolution function learned directly with RL, but suffers from poor training scalability: as training tasks grow, aggregated reward feedback becomes noisy and conflicting, destabilizing training and weakening generalization. We propose DIBS, a decoupled behavioral cloning approach that separates learning task-specific policies from learning the evolution function. We first learn individual teacher policies per task via standard RL, then fit the evolution function via behavioral cloning on teacher-labeled state-action pairs. This replaces noisy reward aggregation with dense, stable supervision. DIBS achieves significant improvements in both training stability and zero-shot generalization against existing RL and meta-RL algorithms.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Placed in Imitation learning methods, one of 13 directions in Offline RL and imitation learning from data. Builds on 35 of its 43 references that are in the map. First posted on arXiv 30 May 2026.

Builds on

35 of 43 references.

Closest ancestors · 2

Same direction, newest first

  1. 2018An Algorithmic Perspective on Imitation Learning16 Nov
  2. 2018Behavioral Cloning from Observation4 May

Other references · 33

  1. 2017Model-Agnostic Meta-Learning for Fast Adaptation of Deep Networkscited by 4,897
  2. 2020Meta-Learning in Neural Networks: A Surveycited by 950
  3. 2018IMPALA: Scalable Distributed Deep-RL with Importance Weighted Actor-Learner Architecturescited by 883
  4. 2015End-to-End Training of Deep Visuomotor Policiescited by 875
  5. 2019Leveraging Procedural Generation to Benchmark Reinforcement Learningcited by 483
  6. 2018Quantifying Generalization in Reinforcement Learningcited by 352
  7. 2017Distral: Robust Multitask Reinforcement Learningcited by 233
  8. 2019VariBAD: A Very Good Method for Bayes-Adaptive Deep RL via Meta-Learningcited by 217
  9. 2018Programmatically Interpretable Reinforcement Learningcited by 193
  10. 2018Verifiable Reinforcement Learning via Policy Extractioncited by 177
  11. 2018A Study on Overfitting in Deep Reinforcement Learningcited by 174
  12. 2021Multi-Task Reinforcement Learning with Context-based Representationscited by 174
21 more
  1. 2021A Survey of Zero-shot Generalisation in Deep Reinforcement Learningcited by 170
  2. 2022Goal-Conditioned Reinforcement Learning: Problems and Solutionscited by 158
  3. 2016Reinforcement Learning With Temporal Logic Rewardscited by 117
  4. 2017Zero-Shot Task Generalization with Multi-Task Deep Reinforcement Learningcited by 98
  5. 2019Reinforcement Learning for Temporal Logic Control Synthesis with Probabilistic Satisfaction Guaranteescited by 77
  6. 2018Foundations for Restraining Bolts: Reinforcement Learning with LTLf/LDLf restraining specificationscited by 72
  7. 2020A Composable Specification Language for Reinforcement Learning Taskscited by 69
  8. 2023Constrained Decision Transformer for Offline Safe Reinforcement Learningcited by 69
  9. 2016Q-Learning for Robust Satisfaction of Signal Temporal Logic Specificationscited by 67
  10. 2021Compositional Reinforcement Learning from Logical Specificationscited by 67
  11. 2018Logically-Constrained Reinforcement Learningcited by 51
  12. 2018Hierarchical Reinforcement Learning for Zero-shot Generalization with Subtask Dependenciescited by 43
  13. 2019An Inductive Synthesis Framework for Verifiable Reinforcement Learningcited by 39
  14. 2019Transfer of Temporal Logic Formulas in Reinforcement Learningcited by 31
  15. 2019Modular Deep Reinforcement Learning with Temporal Logic Specificationscited by 25
  16. 2021On the (In)Tractability of Reinforcement Learning for LTL Objectivescited by 18
  17. 2022GALOIS: Boosting Deep Reinforcement Learning via Generalizable Logic Synthesiscited by 16
  18. 2022Specification-Guided Learning of Nash Equilibria with High Social Welfarecited by 8
  19. 2025One Subgoal at a Time: Zero-Shot Generalization to Arbitrary Linear Temporal Logic Requirements in Multi-Task Reinforcement Learningcited by 8
  20. 2024Inductive Generalization in Reinforcement Learning from Specificationscited by 3
  21. 2020C-Learning: Horizon-Aware Cumulative Accessibility Estimationcited by 2

Built on by

Not cited yet.

Similar, not cited

Close in wording, no citation either way

  1. 2022Know Your Boundaries: The Necessity of Explicit Behavioral Cloning in Offline RL
  2. 2019Integrating Behavior Cloning and Reinforcement Learning for Improved Performance in Dense and Sparse Reward Environments
  3. 2026From Imitation to Reward Discovery: On-Policy Warmup for Agentic RL
  4. 2025Posterior Behavioral Cloning: Pretraining BC Policies for Efficient RL Finetuning
  5. 2025Generalizing Behavior via Inverse Reinforcement Learning with Closed-Form Reward Centroids
  6. 2024Policy Agnostic RL: Offline RL and Online RL Fine-Tuning of Any Class and Backbone
  7. 2022Data augmentation for efficient learning from parametric experts
  8. 2026Reinforcement Learning with Decomposed Subtasks