Guardado en:
| Autores principales: | , , |
|---|---|
| Formato: | Preprint |
| Publicado: |
2025
|
| Materias: | |
| Acceso en línea: | https://arxiv.org/abs/2507.00762 |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| _version_ | 1866912461111689216 |
|---|---|
| author | Maus, Tom Atamna, Asma Glasmachers, Tobias |
| author_facet | Maus, Tom Atamna, Asma Glasmachers, Tobias |
| contents | Reinforcement Learning (RL) has demonstrated significant potential in certain real-world industrial applications, yet its broader deployment remains limited by inherent challenges such as sample inefficiency and unstable learning dynamics. This study investigates the utilization of Genetic Algorithms (GAs) as a mechanism for improving RL performance in an industrially inspired sorting environment. We propose a novel approach in which GA-generated expert demonstrations are used to enhance policy learning. These demonstrations are incorporated into a Deep Q-Network (DQN) replay buffer for experience-based learning and utilized as warm-start trajectories for Proximal Policy Optimization (PPO) agents to accelerate training convergence. Our experiments compare standard RL training with rule-based heuristics, brute-force optimization, and demonstration data, revealing that GA-derived demonstrations significantly improve RL performance. Notably, PPO agents initialized with GA-generated data achieved superior cumulative rewards, highlighting the potential of hybrid learning paradigms, where heuristic search methods complement data-driven RL. The utilized framework is publicly available and enables further research into adaptive RL strategies for real-world applications. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2507_00762 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Leveraging Genetic Algorithms for Efficient Demonstration Generation in Real-World Reinforcement Learning Environments Maus, Tom Atamna, Asma Glasmachers, Tobias Machine Learning Reinforcement Learning (RL) has demonstrated significant potential in certain real-world industrial applications, yet its broader deployment remains limited by inherent challenges such as sample inefficiency and unstable learning dynamics. This study investigates the utilization of Genetic Algorithms (GAs) as a mechanism for improving RL performance in an industrially inspired sorting environment. We propose a novel approach in which GA-generated expert demonstrations are used to enhance policy learning. These demonstrations are incorporated into a Deep Q-Network (DQN) replay buffer for experience-based learning and utilized as warm-start trajectories for Proximal Policy Optimization (PPO) agents to accelerate training convergence. Our experiments compare standard RL training with rule-based heuristics, brute-force optimization, and demonstration data, revealing that GA-derived demonstrations significantly improve RL performance. Notably, PPO agents initialized with GA-generated data achieved superior cumulative rewards, highlighting the potential of hybrid learning paradigms, where heuristic search methods complement data-driven RL. The utilized framework is publicly available and enables further research into adaptive RL strategies for real-world applications. |
| title | Leveraging Genetic Algorithms for Efficient Demonstration Generation in Real-World Reinforcement Learning Environments |
| topic | Machine Learning |
| url | https://arxiv.org/abs/2507.00762 |