mlsanityData to 7 Oct 2026

Adaptation of Quadruped Robot Locomotion with Meta-Learning

arXiv 2107.03741 ↗First posted 8 Jul 2021cs.RO cs.LGcited by 0

Not on the map. Why?

Abstract (arXiv)

Animals have remarkable abilities to adapt locomotion to different terrains and tasks. However, robots trained by means of reinforcement learning are typically able to solve only a single task and a transferred policy is usually inferior to that trained from scratch. In this work, we demonstrate that meta-reinforcement learning can be used to successfully train a robot capable to solve a wide range of locomotion tasks. The performance of the meta-trained robot is similar to that of a robot that is trained on a single task.

Key facts. No citing papers in the map yet (data through 7 Oct 2026). Builds on 35 of its 37 references that are in the map. First posted on arXiv 8 Jul 2021.

Builds on

35 of 37 references.

References · 35

  1. 2017Model-Agnostic Meta-Learning for Fast Adaptation of Deep Networkscited by 4,861
  2. 2018Soft Actor-Critic: Off-Policy Maximum Entropy Deep Reinforcement Learning with a Stochastic Actorcited by 4,635
  3. 2013Auto-Encoding Variational Bayescited by 3,980
  4. 2018Addressing Function Approximation Error in Actor-Critic Methodscited by 2,302
  5. 2015High-Dimensional Continuous Control Using Generalized Advantage Estimationcited by 1,916
  6. 2017Domain Randomization for Transferring Deep Neural Networks from Simulation to the Real Worldcited by 1,401
  7. 2018Soft Actor-Critic Algorithms and Applicationscited by 1,179
  8. 2019Meta-World: A Benchmark and Evaluation for Multi-Task and Meta Reinforcement Learningcited by 1,168
  9. 2016Deep Variational Information Bottleneckcited by 915
  10. 2018QT-Opt: Scalable Deep Reinforcement Learning for Vision-Based Robotic Manipulationcited by 730
  11. 2019Solving Rubik's Cube with a Robot Handcited by 699
  12. 2018Learning Dexterous In-Hand Manipulationcited by 643
23 more
  1. 2017Sim-to-Real Transfer of Robotic Control with Dynamics Randomizationcited by 616
  2. 2020Learning Quadrupedal Locomotion over Challenging Terraincited by 494
  3. 2016RL2: Fast Reinforcement Learning via Slow Reinforcement Learningcited by 490
  4. 2020Sim-to-Real Transfer in Deep Reinforcement Learning for Robotics: a Surveycited by 388
  5. 2019Efficient Off-Policy Meta-Reinforcement Learning via Probabilistic Context Variablescited by 372
  6. 2017Deep Reinforcement Learning: An Overviewcited by 327
  7. 2018Learning to Adapt in Dynamic, Real-World Environments Through Meta-Reinforcement Learningcited by 270
  8. 2019VariBAD: A Very Good Method for Bayes-Adaptive Deep RL via Meta-Learningcited by 210
  9. 2019Deep Dynamics Models for Learning Dexterous Manipulationcited by 200
  10. 2019Active Domain Randomizationcited by 161
  11. 2020Controlling Overestimation Bias with Truncated Mixture of Continuous Distributional Quantile Criticscited by 154
  12. 2018Learning to Walk via Deep Reinforcement Learningcited by 153
  13. 2017Using Simulation and Domain Adaptation to Improve Efficiency of Deep Robotic Graspingcited by 138
  14. 2019TossingBot: Learning to Throw Arbitrary Objects with Residual Physicscited by 131
  15. 2020Offline Meta-Reinforcement Learning with Advantage Weightingcited by 92
  16. 2018Dexterous Manipulation with Deep Reinforcement Learning: Efficient, General, and Low-Costcited by 79
  17. 2019ROBEL: Robotics Benchmarks for Learning with Low-Cost Robotscited by 70
  18. 2021Auto-Tuned Sim-to-Real Transfercited by 45
  19. 2019Multi-Agent Manipulation via Locomotion using Hierarchical Sim2Realcited by 39
  20. 2020Emergent Real-World Robotic Skills via Unsupervised Off-Policy Reinforcement Learningcited by 30
  21. 2018Grasp2Vec: Learning Object Representations from Self-Supervised Graspingcited by 27
  22. 2020MELD: Meta-Reinforcement Learning from Images via Latent State Modelscited by 22
  23. 2020Interferobot: aligning an optical interferometer by a reinforcement learning agentcited by 12

Built on by

Not cited yet.