Explorative Imitation Learning: A Path Signature Approach for Continuous Environments
Fuente:
arXiv
Salvato in:
| Autori principali: | , , , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2024
|
| Soggetti: | |
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866914881220902912 |
|---|---|
| author | Gavenski, Nathan Monteiro, Juarez Meneguzzi, Felipe Luck, Michael Rodrigues, Odinaldo |
| author_facet | Gavenski, Nathan Monteiro, Juarez Meneguzzi, Felipe Luck, Michael Rodrigues, Odinaldo |
| contents | Some imitation learning methods combine behavioural cloning with self-supervision to infer actions from state pairs. However, most rely on a large number of expert trajectories to increase generalisation and human intervention to capture key aspects of the problem, such as domain constraints. In this paper, we propose Continuous Imitation Learning from Observation (CILO), a new method augmenting imitation learning with two important features: (i) exploration, allowing for more diverse state transitions, requiring less expert trajectories and resulting in fewer training iterations; and (ii) path signatures, allowing for automatic encoding of constraints, through the creation of non-parametric representations of agents and expert trajectories. We compared CILO with a baseline and two leading imitation learning methods in five environments. It had the best overall performance of all methods in all environments, outperforming the expert in two of them. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2407_04856 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Explorative Imitation Learning: A Path Signature Approach for Continuous Environments Gavenski, Nathan Monteiro, Juarez Meneguzzi, Felipe Luck, Michael Rodrigues, Odinaldo Machine Learning Artificial Intelligence Some imitation learning methods combine behavioural cloning with self-supervision to infer actions from state pairs. However, most rely on a large number of expert trajectories to increase generalisation and human intervention to capture key aspects of the problem, such as domain constraints. In this paper, we propose Continuous Imitation Learning from Observation (CILO), a new method augmenting imitation learning with two important features: (i) exploration, allowing for more diverse state transitions, requiring less expert trajectories and resulting in fewer training iterations; and (ii) path signatures, allowing for automatic encoding of constraints, through the creation of non-parametric representations of agents and expert trajectories. We compared CILO with a baseline and two leading imitation learning methods in five environments. It had the best overall performance of all methods in all environments, outperforming the expert in two of them. |
| title | Explorative Imitation Learning: A Path Signature Approach for Continuous Environments |
| topic | Machine Learning Artificial Intelligence |
| url | https://arxiv.org/abs/2407.04856 |