K-Myriad: Jump-starting reinforcement learning with unsupervised parallel agents
Fuente:
arXiv
Enregistré dans:
| Auteurs principaux: | , , , |
|---|---|
| Format: | Preprint |
| Publié: |
2026
|
| Sujets: | |
| Accès en ligne: | |
| Tags: |
Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
|
| _version_ | 1866911399503986688 |
|---|---|
| author | De Paola, Vincenzo Mutti, Mirco Zamboni, Riccardo Restelli, Marcello |
| author_facet | De Paola, Vincenzo Mutti, Mirco Zamboni, Riccardo Restelli, Marcello |
| contents | Parallelization in Reinforcement Learning is typically employed to speed up the training of a single policy, where multiple workers collect experience from an identical sampling distribution. This common design limits the potential of parallelization by neglecting the advantages of diverse exploration strategies. We propose K-Myriad, a scalable and unsupervised method that maximizes the collective state entropy induced by a population of parallel policies. By cultivating a portfolio of specialized exploration strategies, K-Myriad provides a robust initialization for Reinforcement Learning, leading to both higher training efficiency and the discovery of heterogeneous solutions. Experiments on high-dimensional continuous control tasks, with large-scale parallelization, demonstrate that K-Myriad can learn a broad set of distinct policies, highlighting its effectiveness for collective exploration and paving the way towards novel parallelization strategies. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2601_18580 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | K-Myriad: Jump-starting reinforcement learning with unsupervised parallel agents De Paola, Vincenzo Mutti, Mirco Zamboni, Riccardo Restelli, Marcello Machine Learning Parallelization in Reinforcement Learning is typically employed to speed up the training of a single policy, where multiple workers collect experience from an identical sampling distribution. This common design limits the potential of parallelization by neglecting the advantages of diverse exploration strategies. We propose K-Myriad, a scalable and unsupervised method that maximizes the collective state entropy induced by a population of parallel policies. By cultivating a portfolio of specialized exploration strategies, K-Myriad provides a robust initialization for Reinforcement Learning, leading to both higher training efficiency and the discovery of heterogeneous solutions. Experiments on high-dimensional continuous control tasks, with large-scale parallelization, demonstrate that K-Myriad can learn a broad set of distinct policies, highlighting its effectiveness for collective exploration and paving the way towards novel parallelization strategies. |
| title | K-Myriad: Jump-starting reinforcement learning with unsupervised parallel agents |
| topic | Machine Learning |
| url | https://arxiv.org/abs/2601.18580 |