Learning to Play Air Hockey with Model-Based Deep Reinforcement Learning
Fuente:
arXiv
Salvato in:
| Autore principale: | |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2024
|
| Soggetti: | |
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866913373855154176 |
|---|---|
| author | Orsula, Andrej |
| author_facet | Orsula, Andrej |
| contents | In the context of addressing the Robot Air Hockey Challenge 2023, we investigate the applicability of model-based deep reinforcement learning to acquire a policy capable of autonomously playing air hockey. Our agents learn solely from sparse rewards while incorporating self-play to iteratively refine their behaviour over time. The robotic manipulator is interfaced using continuous high-level actions for position-based control in the Cartesian plane while having partial observability of the environment with stochastic transitions. We demonstrate that agents are prone to overfitting when trained solely against a single playstyle, highlighting the importance of self-play for generalization to novel strategies of unseen opponents. Furthermore, the impact of the imagination horizon is explored in the competitive setting of the highly dynamic game of air hockey, with longer horizons resulting in more stable learning and better overall performance. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2406_00518 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Learning to Play Air Hockey with Model-Based Deep Reinforcement Learning Orsula, Andrej Robotics Artificial Intelligence Machine Learning In the context of addressing the Robot Air Hockey Challenge 2023, we investigate the applicability of model-based deep reinforcement learning to acquire a policy capable of autonomously playing air hockey. Our agents learn solely from sparse rewards while incorporating self-play to iteratively refine their behaviour over time. The robotic manipulator is interfaced using continuous high-level actions for position-based control in the Cartesian plane while having partial observability of the environment with stochastic transitions. We demonstrate that agents are prone to overfitting when trained solely against a single playstyle, highlighting the importance of self-play for generalization to novel strategies of unseen opponents. Furthermore, the impact of the imagination horizon is explored in the competitive setting of the highly dynamic game of air hockey, with longer horizons resulting in more stable learning and better overall performance. |
| title | Learning to Play Air Hockey with Model-Based Deep Reinforcement Learning |
| topic | Robotics Artificial Intelligence Machine Learning |
| url | https://arxiv.org/abs/2406.00518 |