Explore the Context: Optimal Data Collection for Context-Conditional Dynamics Models
Fuente:
arXiv
Salvato in:
| Autori principali: | , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2021
|
| Soggetti: | |
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866913532289744896 |
|---|---|
| author | Achterhold, Jan Stueckler, Joerg |
| author_facet | Achterhold, Jan Stueckler, Joerg |
| contents | In this paper, we learn dynamics models for parametrized families of dynamical systems with varying properties. The dynamics models are formulated as stochastic processes conditioned on a latent context variable which is inferred from observed transitions of the respective system. The probabilistic formulation allows us to compute an action sequence which, for a limited number of environment interactions, optimally explores the given system within the parametrized family. This is achieved by steering the system through transitions being most informative for the context variable. We demonstrate the effectiveness of our method for exploration on a non-linear toy-problem and two well-known reinforcement learning environments. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2102_11394 |
| institution | arXiv |
| publishDate | 2021 |
| record_format | arxiv |
| spellingShingle | Explore the Context: Optimal Data Collection for Context-Conditional Dynamics Models Achterhold, Jan Stueckler, Joerg Machine Learning Robotics Systems and Control In this paper, we learn dynamics models for parametrized families of dynamical systems with varying properties. The dynamics models are formulated as stochastic processes conditioned on a latent context variable which is inferred from observed transitions of the respective system. The probabilistic formulation allows us to compute an action sequence which, for a limited number of environment interactions, optimally explores the given system within the parametrized family. This is achieved by steering the system through transitions being most informative for the context variable. We demonstrate the effectiveness of our method for exploration on a non-linear toy-problem and two well-known reinforcement learning environments. |
| title | Explore the Context: Optimal Data Collection for Context-Conditional Dynamics Models |
| topic | Machine Learning Robotics Systems and Control |
| url | https://arxiv.org/abs/2102.11394 |