mlsanityData to 14 Oct 2026

Continual Reinforcement Learning deployed in Real-life using Policy Distillation and Sim2Real Transfer

arXiv 1906.04452 ↗First posted 11 Jun 2019cs.LG cs.RO stat.MLcited by 26

Not on the map. Why?

Abstract (arXiv)

We focus on the problem of teaching a robot to solve tasks presented sequentially, i.e., in a continual learning scenario. The robot should be able to solve all tasks it has encountered, without forgetting past tasks. We provide preliminary work on applying Reinforcement Learning to such setting, on 2D navigation tasks for a 3 wheel omni-directional robot. Our approach takes advantage of state representation learning and policy distillation. Policies are trained using learned features as input, rather than raw observations, allowing better sample efficiency. Policy distillation is used to combine multiple policies into a single one that solves all encountered tasks.

Key facts. Cited by 26 papers in the map (data through 14 Oct 2026). First posted on arXiv 11 Jun 2019.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2021: 5; 2022: 7; 2023: 5; 2024: 5; 2025: 3; 2026: 1.

26 papers.

Sort:

By area:

  1. 2024Flow as the Cross-Domain Manipulation Interfacecited by 132
  2. 2022Continual Learning with Foundation Models: An Empirical Study of Latent Replaycited by 61
  3. 2023Connecting the Dots in Trustworthy Artificial Intelligence: From AI Principles, Ethics, and Key Requirements to Responsible AI Systems and Regulationcited by 61
  4. 2022Visual Reinforcement Learning with Self-Supervised 3D Representationscited by 45
  5. 2021Reinforcement Learning for Ridesharing: An Extended Surveycited by 35
  6. 2021Continuum: Simple Management of Complex Continual Learning Scenarioscited by 33
  7. 2021CRIL: Continual Robot Imitation Learning via Generative and Prediction Modelcited by 24
  8. 2025A Survey of Continual Reinforcement Learningcited by 18
  9. 2024QuasiSim: Parameterized Quasi-Physical Simulators for Dexterous Manipulations Transfercited by 12
  10. 2022Beyond Supervised Continual Learning: a Reviewcited by 11
  11. 2022Cyclic Policy Distillation: Sample-Efficient Sim-to-Real Reinforcement Learning with Domain Randomizationcited by 8
  12. 2024Continual Domain Randomizationcited by 8
14 more
  1. 2021Procedural Content Generation: Better Benchmarks for Transfer Reinforcement Learningcited by 7
  2. 2022Self-Activating Neural Ensembles for Continual Reinforcement Learningcited by 7
  3. 2023A Platform-Agnostic Deep Reinforcement Learning Framework for Effective Sim2Real Transfer towards Autonomous Drivingcited by 7
  4. 2022Coach-assisted Multi-Agent Reinforcement Learning Framework for Unexpected Crashed Agentscited by 3
  5. 2022On the Verge of Solving Rocket League using Deep Reinforcement Learning and Sim-to-sim Transfercited by 2
  6. 2023Vision-based DRL Autonomous Driving Agent with Sim2Real Transfercited by 2
  7. 2023Robust Navigation with Cross-Modal Fusion and Knowledge Transfercited by 2
  8. 2024Data-Driven Simulator for Mechanical Circulatory Support with Domain Adversarial Neural Processcited by 2
  9. 2025Pessimism Principle Can Be Effective: Towards a Framework for Zero-Shot Transfer Reinforcement Learningcited by 2
  10. 2021Offline RL With Resource Constrained Online Deploymentcited by 1
  11. 2023Using Curiosity for an Even Representation of Tasks in Continual Offline Reinforcement Learningcited by 1
  12. 2024Whisker-Inspired Tactile Sensing: A Sim2Real Approach for Precise Underwater Contact Trackingcited by 1
  13. 2025Learning more with the same effort: how randomization improves the robustness of a robotic deep reinforcement learning agentcited by 1
  14. 2026CIDER: Continual Interactive Distillation for Embodied Reinforcement Learningcited by 1