Hierarchical Behaviour Spaces
Fuente:
arXiv
Salvato in:
| Autori principali: | , , , , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2026
|
| Soggetti: | |
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866913065573810176 |
|---|---|
| author | Matthews, Michael Tryfan Kanervisto, Anssi Foerster, Jakob D'Oro, Pierluca Fujimoto, Scott Henaff, Mikael |
| author_facet | Matthews, Michael Tryfan Kanervisto, Anssi Foerster, Jakob D'Oro, Pierluca Fujimoto, Scott Henaff, Mikael |
| contents | Recent work in hierarchical reinforcement learning has shown success in scaling to billions of timesteps when learning over a set of predefined option reward functions. We show that, instead of using a single reward function per option, the reward functions can be effectively used to induce a space of behaviours, by letting the controller specify linear combinations over reward functions, allowing a more expressive set of policies to be represented. We call this method Hierarchical Behaviour Spaces (HBS). We evaluate HBS on the NetHack Learning Environment, demonstrating strong performance. We conduct a series of experiments and determine that, perhaps going against conventional wisdom, the benefits of hierarchy in our method come from increased exploration rather than long term reasoning. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2604_24558 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | Hierarchical Behaviour Spaces Matthews, Michael Tryfan Kanervisto, Anssi Foerster, Jakob D'Oro, Pierluca Fujimoto, Scott Henaff, Mikael Artificial Intelligence Machine Learning Recent work in hierarchical reinforcement learning has shown success in scaling to billions of timesteps when learning over a set of predefined option reward functions. We show that, instead of using a single reward function per option, the reward functions can be effectively used to induce a space of behaviours, by letting the controller specify linear combinations over reward functions, allowing a more expressive set of policies to be represented. We call this method Hierarchical Behaviour Spaces (HBS). We evaluate HBS on the NetHack Learning Environment, demonstrating strong performance. We conduct a series of experiments and determine that, perhaps going against conventional wisdom, the benefits of hierarchy in our method come from increased exploration rather than long term reasoning. |
| title | Hierarchical Behaviour Spaces |
| topic | Artificial Intelligence Machine Learning |
| url | https://arxiv.org/abs/2604.24558 |