mlsanityData to 7 Oct 2026

DisCoRL: Continual Reinforcement Learning via Policy Distillation

arXiv 1907.05855 ↗First posted 11 Jul 2019cs.LG cs.AI stat.MLcited by 35

Not on the map. Why?

Abstract (arXiv)

In multi-task reinforcement learning there are two main challenges: at training time, the ability to learn different policies with a single model; at test time, inferring which of those policies applying without an external signal. In the case of continual reinforcement learning a third challenge arises: learning tasks sequentially without forgetting the previous ones. In this paper, we tackle these challenges by proposing DisCoRL, an approach combining state representation learning and policy distillation. We experiment on a sequence of three simulated 2D navigation tasks with a 3 wheel omni-directional robot. Moreover, we tested our approach's robustness by transferring the final policy into a real life setting. The policy can solve all tasks and automatically infer which one to run.

Key facts. Cited by 35 papers in the map (data through 7 Oct 2026). First posted on arXiv 11 Jul 2019.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 8; 2022: 9; 2023: 7; 2024: 6; 2025: 4; 2026: 1.

35 papers.

Sort:

By area:

  1. 2021Acquisition of Chess Knowledge in AlphaZerocited by 120
  2. 2022Continual Learning with Foundation Models: An Empirical Study of Latent Replaycited by 61
  3. 2024Sparse Diffusion Policy: A Sparse, Reusable, and Flexible Policy for Robot Learningcited by 56
  4. 2023TAIL: Task-specific Adapters for Imitation Learning with Large Pretrained Modelscited by 48
  5. 2023Bridging the Human-AI Knowledge Gap: Concept Discovery and Transfer in AlphaZerocited by 41
  6. 2021Understanding Continual Learning Settings with Data Distribution Drift Analysiscited by 38
  7. 2021Continuum: Simple Management of Complex Continual Learning Scenarioscited by 33
  8. 2022Disentangling Transfer in Continual Reinforcement Learningcited by 31
  9. 2024Multi-Agent Reinforcement Learning for Autonomous Driving: A Surveycited by 30
  10. 2022Building a Subspace of Policies for Scalable Continual Learningcited by 28
  11. 2024Fine-tuning Reinforcement Learning Models is Secretly a Forgetting Mitigation Problemcited by 23
  12. 2021Sequoia: A Software Framework to Unify Continual Learning Researchcited by 19
23 more
  1. 2025A Survey of Continual Reinforcement Learningcited by 16
  2. 2021Tackling Catastrophic Forgetting and Background Shift in Continual Semantic Segmentationcited by 15
  3. 2021Catastrophic Interference in Reinforcement Learning: A Solution Based on Context Division and Knowledge Distillationcited by 15
  4. 2023Guided Online Distillation: Promoting Safe Reinforcement Learning by Offline Demonstrationcited by 14
  5. 2022Dynamics-Adaptive Continual Reinforcement Learning via Progressive Contextualizationcited by 13
  6. 2022Beyond Supervised Continual Learning: a Reviewcited by 11
  7. 2022Task-Agnostic Continual Reinforcement Learning: Gaining Insights and Overcoming Challengescited by 10
  8. 2022Continual Vision-based Reinforcement Learning with Group Symmetriescited by 10
  9. 2023Guarded Policy Optimization with Imperfect Online Demonstrationscited by 10
  10. 2023Replay-enhanced Continual Reinforcement Learningcited by 6
  11. 2022Forgetting and Imbalance in Robot Lifelong Learning with Off-policy Datacited by 5
  12. 2025Continual Reinforcement Learning via Autoencoder-Driven Task and New Environment Recognitioncited by 5
  13. 2024Continual Policy Distillation of Reinforcement Learning-based Controllers for Soft Robotic In-Hand Manipulationcited by 4
  14. 2023Counterfactual Explainer Framework for Deep Reinforcement Learning Models Using Policy Distillationcited by 3
  15. 2021Deep Learning for Embodied Vision Navigation: A Surveycited by 2
  16. 2021A Simple Approach to Continual Learning by Transferring Skill Parameterscited by 2
  17. 2025Overcoming Non-stationary Dynamics with Evidential Proximal Policy Optimizationcited by 2
  18. 2025Pessimism Principle Can Be Effective: Towards a Framework for Zero-Shot Transfer Reinforcement Learningcited by 2
  19. 2022Decoding surface codes with deep reinforcement learning and probabilistic policy reusecited by 1
  20. 2023Using Curiosity for an Even Representation of Tasks in Continual Offline Reinforcement Learningcited by 1
  21. 2024Continual Model-based Reinforcement Learning for Data Efficient Wireless Network Optimisationcited by 1
  22. 2026Continual Policy Consolidation for Lifelong Robot Learningcited by 1
  23. 2024Natural Policy Gradient and Actor Critic Methods for Constrained Multi-Task Reinforcement Learningcited by 0