mlsanityData to 7 Oct 2026

Random Actions vs Random Policies: Bootstrapping Model-Based Direct Policy Search

arXiv 2210.11801 ↗First posted 21 Oct 2022cs.LGcited by 0

Not on the map. Why?

Abstract (arXiv)

This paper studies the impact of the initial data gathering method on the subsequent learning of a dynamics model. Dynamics models approximate the true transition function of a given task, in order to perform policy search directly on the model rather than on the costly real system. This study aims to determine how to bootstrap a model as efficiently as possible, by comparing initialization methods employed in two different policy search frameworks in the literature. The study focuses on the model performance under the episode-based framework of Evolutionary methods using probabilistic ensembles. Experimental results show that various task-dependant factors can be detrimental to each method, suggesting to explore hybrid approaches.

Key facts. No citing papers in the map yet (data through 7 Oct 2026). Builds on 13 of its 30 references that are in the map. First posted on arXiv 21 Oct 2022.

Builds on

13 of 30 references.

References · 13

  1. 2017Domain Randomization for Transferring Deep Neural Networks from Simulation to the Real Worldcited by 1,401
  2. 2018Learning Latent Dynamics for Planning from Pixelscited by 1,221
  3. 2018Deep Reinforcement Learning in a Handful of Trials using Probabilistic Dynamics Modelscited by 748
  4. 2020Planning to Explore via Self-Supervised World Modelscited by 365
  5. 2019Dynamics-Aware Unsupervised Discovery of Skillscited by 308
  6. 2017Neural Network Dynamics for Model-Based Deep Reinforcement Learning with Model-Free Fine-Tuningcited by 288
  7. 2017Quality and Diversity Optimization: A Unifying Modular Frameworkcited by 111
  8. 2018Data-Efficient Design Exploration through Surrogate-Assisted Illuminationcited by 38
  9. 2021Dynamics-Aware Quality-Diversity for Efficient Learning of Skill Repertoirescited by 20
  10. 2020Model-Based Quality-Diversity Search for Efficient Robot Learningcited by 14
  11. 2018Policy Search in Continuous Action Domains: an Overviewcited by 10
  12. 2022Automatic Acquisition of a Repertoire of Diverse Grasping Trajectories through Behavior Shaping and Novelty Searchcited by 9
1 more
  1. 2022Learning to Walk Autonomously via Reset-Free Quality-Diversitycited by 7

Built on by

Not cited yet.