Backward Learning for Goal-Conditioned Policies
Fuente:
arXiv
Enregistré dans:
| Auteurs principaux: | , , |
|---|---|
| Format: | Preprint |
| Publié: |
2023
|
| Sujets: | |
| Accès en ligne: | |
| Tags: |
Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
|
| _version_ | 1866929313016709120 |
|---|---|
| author | Höftmann, Marc Robine, Jan Harmeling, Stefan |
| author_facet | Höftmann, Marc Robine, Jan Harmeling, Stefan |
| contents | Can we learn policies in reinforcement learning without rewards? Can we learn a policy just by trying to reach a goal state? We answer these questions positively by proposing a multi-step procedure that first learns a world model that goes backward in time, secondly generates goal-reaching backward trajectories, thirdly improves those sequences using shortest path finding algorithms, and finally trains a neural network policy by imitation learning. We evaluate our method on a deterministic maze environment where the observations are $64\times 64$ pixel bird's eye images and can show that it consistently reaches several goals. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2312_05044 |
| institution | arXiv |
| publishDate | 2023 |
| record_format | arxiv |
| spellingShingle | Backward Learning for Goal-Conditioned Policies Höftmann, Marc Robine, Jan Harmeling, Stefan Machine Learning Artificial Intelligence Can we learn policies in reinforcement learning without rewards? Can we learn a policy just by trying to reach a goal state? We answer these questions positively by proposing a multi-step procedure that first learns a world model that goes backward in time, secondly generates goal-reaching backward trajectories, thirdly improves those sequences using shortest path finding algorithms, and finally trains a neural network policy by imitation learning. We evaluate our method on a deterministic maze environment where the observations are $64\times 64$ pixel bird's eye images and can show that it consistently reaches several goals. |
| title | Backward Learning for Goal-Conditioned Policies |
| topic | Machine Learning Artificial Intelligence |
| url | https://arxiv.org/abs/2312.05044 |