mlsanityData to 14 Oct 2026

Policy Distillation

arXiv 1511.06295 ↗First posted 19 Nov 2015cs.LGcited by 440

Not on the map. Why?

Cited by 104 in Knowledge distillation, but placed by its own abstract, which didn’t fit.

Abstract (arXiv)

Policies for complex visual tasks have been successfully learned with deep reinforcement learning, using an approach called deep Q-networks (DQN), but relatively large (task-specific) networks and extensive training are needed to achieve good performance. In this work, we present a novel method called policy distillation that can be used to extract the policy of a reinforcement learning agent and train a new network that performs at the expert level while being dramatically smaller and more efficient. Furthermore, the same method can be used to consolidate multiple task-specific policies into a single policy. We demonstrate these claims using the Atari domain and show that the multi-task distilled agent outperforms the single-task teachers as well as a jointly-trained DQN agent.

Key facts. Cited by 440 papers in the map (data through 14 Oct 2026). First posted on arXiv 19 Nov 2015.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2019: 5; 2020: 2; 2021: 61; 2022: 52; 2023: 47; 2024: 42; 2025: 54; 2026: 177.

440 papers.

Sort:

By area:

  1. 2026GLM-5: from Vibe Coding to Agentic Engineeringcited by 587
  2. 2025SpatialVLA: Exploring Spatial Representations for Visual-Language-Action Modelcited by 519
  3. 2021Conflict-Averse Gradient Descent for Multi-task Learningcited by 459
  4. 2026Self-Distilled Reasoner: On-Policy Self-Distillation for Large Language Modelscited by 455
  5. 2024Rewarding Progress: Scaling Automated Process Verifiers for LLM Reasoningcited by 279
  6. 2021MT-Opt: Continuous Multi-Task Robotic Reinforcement Learning at Scalecited by 229
  7. 2022Multi-Game Decision Transformerscited by 214
  8. 2021How to Train Your Robot with Deep Reinforcement Learning; Lessons We've Learnedcited by 213
  9. 2026MiMo-V2-Flash Technical Reportcited by 191
  10. 2022In-context Reinforcement Learning with Algorithm Distillationcited by 190
  11. 2026Learning beyond Teacher: Generalized On-Policy Distillation with Reward Extrapolationcited by 184
  12. 2026Entropy-Aware On-Policy Distillation of Language Modelscited by 175
38 more
  1. 2021Multi-Task Reinforcement Learning with Context-based Representationscited by 174
  2. 2021Towards Understanding Knowledge Distillationcited by 158
  3. 2023MiniLLM: On-Policy Distillation of Large Language Modelscited by 139
  4. 2023Learning Agile Soccer Skills for a Bipedal Robot with Deep Reinforcement Learningcited by 133
  5. 2022Understanding and Preventing Capacity Loss in Reinforcement Learningcited by 125
  6. 2023Universal Humanoid Motion Representations for Physics-Based Controlcited by 116
  7. 2023Policy Expansion for Bridging Offline-to-Online Reinforcement Learningcited by 104
  8. 2021Reset-Free Reinforcement Learning via Multi-Task Learning: Learning Dexterous Manipulation Behaviors without Human Interventioncited by 95
  9. 2025Inference-Time Alignment in Diffusion Models with Reward-Guided Generation: Tutorial and Reviewcited by 88
  10. 2026Vision-OPD: Learning to See Fine Details for Multimodal LLMs via On-Policy Self-Distillationcited by 77
  11. 2021A Survey on Interpretable Reinforcement Learningcited by 73
  12. 2022Offline Q-Learning on Diverse Multi-Task Data Both Scales And Generalizescited by 73
  13. 2021Beyond Pick-and-Place: Tackling Robotic Stacking of Diverse Shapescited by 71
  14. 2022In Defense of the Unitary Scalarization for Deep Multi-Task Learningcited by 67
  15. 2021Conservative Data Sharing for Multi-Task Offline Reinforcement Learningcited by 64
  16. 2021Robot Learning from Randomized Simulations: A Reviewcited by 63
  17. 2022Learning Generalizable Models for Vehicle Routing Problems via Knowledge Distillationcited by 62
  18. 2024TRANSIC: Sim-to-Real Policy Transfer by Learning from Online Correctioncited by 59
  19. 2025RealSafe-R1: Safety-Aligned DeepSeek-R1 without Compromising Reasoning Capabilitycited by 59
  20. 2024Sparse Diffusion Policy: A Sparse, Reusable, and Flexible Policy for Robot Learningcited by 57
  21. 2026Expanding the Capabilities of Reinforcement Learning via Text Feedbackcited by 53
  22. 2023Sequential Dexterity: Chaining Dexterous Policies for Long-Horizon Manipulationcited by 49
  23. 2023PADL: Language-Directed Physics-Based Character Controlcited by 48
  24. 2024Learning from Teaching Regularization: Generalizable Correlations Should be Easy to Imitatecited by 47
  25. 2021Bootstrapped Meta-Learningcited by 45
  26. 2024Sharing Knowledge in Multi-Task Deep Reinforcement Learningcited by 44
  27. 2021SECANT: Self-Expert Cloning for Zero-Shot Generalization of Visual Policiescited by 43
  28. 2021Deep Multiagent Reinforcement Learning: Challenges and Directionscited by 42
  29. 2021Interesting Object, Curious Agent: Learning Task-Agnostic Explorationcited by 38
  30. 2023Neural Categorical Priors for Physics-Based Character Controlcited by 38
  31. 2023Lifelike Agility and Play in Quadrupedal Robots using Reinforcement Learning and Generative Pre-trained Modelscited by 37
  32. 2022On Transforming Reinforcement Learning by Transformer: The Development Trajectorycited by 36
  33. 2026Video-OPD: Efficient Post-Training of Multimodal Large Language Models for Temporal Video Grounding via On-Policy Distillationcited by 36
  34. 2021Efficient Transformers in Reinforcement Learning using Actor-Learner Distillationcited by 35
  35. 2021Lifelong Robotic Reinforcement Learning by Retaining Experiencescited by 34
  36. 2022A System-Level View on Out-of-Distribution Data in Roboticscited by 33
  37. 2023Explainable Deep Reinforcement Learning: State of the Art and Challengescited by 33
  38. 2026OPID: On-Policy Skill Distillation for Agentic Reinforcement Learningcited by 32

50 most cited of 440 All 440 (JSON)