mlsanityData to 14 Oct 2026

Foundational Policy Acquisition via Multitask Learning for Motor Skill Generation

arXiv 2308.16471 ↗First posted 31 Aug 2023cs.RO cs.LGcited by 0

Not on the map. Why?

Abstract (arXiv)

In this study, we propose a multitask reinforcement learning algorithm for foundational policy acquisition to generate novel motor skills. textcolorhcolorLearning the rich representation of the multitask policy is a challenge in dynamic movement generation tasks because the policy needs to cope with changes in goals or environments with different reward functions or physical parameters. Inspired by human sensorimotor adaptation mechanisms, we developed the learning pipeline to construct the encoder-decoder networks and network selection to facilitate foundational policy acquisition under multiple situations. First, we compared the proposed method with previous multitask reinforcement learning methods in the standard multi-locomotion tasks. The results showed that the proposed approach outperformed the baseline methods. Then, we applied the proposed method to the ball heading task using a monopod robot model to evaluate skill generation performance. The results showed that the proposed method was able to adapt to novel target positions or inexperienced ball restitution coefficients but to acquire a foundational policy network, originally learned for heading motion, which can generate an entirely new overhead kicking skill.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Builds on 23 of its 48 references that are in the map. First posted on arXiv 31 Aug 2023.

Builds on

23 of 48 references.

References · 23

  1. 2019PyTorch: An Imperative Style, High-Performance Deep Learning Librarycited by 20,305
  2. 2017Model-Agnostic Meta-Learning for Fast Adaptation of Deep Networkscited by 4,897
  3. 2018Soft Actor-Critic: Off-Policy Maximum Entropy Deep Reinforcement Learning with a Stochastic Actorcited by 4,885
  4. 2015Continuous control with deep reinforcement learningcited by 3,407
  5. 2019Optuna: A Next-generation Hyperparameter Optimization Frameworkcited by 2,501
  6. 2018Addressing Function Approximation Error in Actor-Critic Methodscited by 2,417
  7. 2018Soft Actor-Critic Algorithms and Applicationscited by 1,240
  8. 2019Meta-World: A Benchmark and Evaluation for Multi-Task and Meta Reinforcement Learningcited by 1,204
  9. 2017Hindsight Experience Replaycited by 1,136
  10. 2017Evolution Strategies as a Scalable Alternative to Reinforcement Learningcited by 574
  11. 2016RL2: Fast Reinforcement Learning via Slow Reinforcement Learningcited by 503
  12. 2018Reinforcement Learning and Control as Probabilistic Inference: Tutorial and Reviewcited by 482
11 more
  1. 2019Efficient Off-Policy Meta-Reinforcement Learning via Probabilistic Context Variablescited by 389
  2. 2020dm_control: Software and Tasks for Continuous Controlcited by 375
  3. 2018Learning to Adapt in Dynamic, Real-World Environments Through Meta-Reinforcement Learningcited by 276
  4. 2020Learning Agile Robotic Locomotion Skills by Imitating Animalscited by 251
  5. 2021MT-Opt: Continuous Multi-Task Robotic Reinforcement Learning at Scalecited by 229
  6. 2022Goal-Conditioned Reinforcement Learning: Problems and Solutionscited by 158
  7. 2017Preparing for the Unknown: Learning a Universal Policy with Online System Identificationcited by 141
  8. 2018ProMP: Proximal Meta-Policy Searchcited by 91
  9. 2021Benchmarks for Deep Off-Policy Evaluationcited by 89
  10. 2019Sim-to-Real Transfer for Biped Locomotioncited by 56
  11. 2019Contextual Imagined Goals for Self-Supervised Robotic Learningcited by 40

Built on by

Not cited yet.