Efficient state representation with artificial potential fields for reinforcement learning
Abstract In the complex tasks environment, efficient state feature learning is a key factor to improve the performance of the agent’s policy. When encountering a similar new environment, reinforcement learning agents usually need to learn from scratch. However, humans naturally have a common sense o...
| Main Authors: | , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Springer
2023-02-01
|
| Series: | Complex & Intelligent Systems |
| Subjects: | |
| Online Access: | https://doi.org/10.1007/s40747-023-00995-8 |
| Summary: | Abstract In the complex tasks environment, efficient state feature learning is a key factor to improve the performance of the agent’s policy. When encountering a similar new environment, reinforcement learning agents usually need to learn from scratch. However, humans naturally have a common sense of the environment and are able to use prior knowledge to extract environmental state features. Although the prior knowledge may not be fully applicable to the new environment, it is able to speed up the learning process of the state feature. Taking this inspiration, we propose an artificial potential field-based reinforcement learning (APF-RL) method. The method consists of an artificial potential field state feature abstractor (APF-SA) and an artificial potential field intrinsic reward model (APF-IR). The APF-SA can introduce human knowledge to accelerate the learning process of the state feature. The APF-IR can generate an intrinsic reward to reduce the invalid exploration and guide the learning of the agent’s policy. We conduct experiments on PySC2 with different mini-games. The experimental results show that the APF-RL method achieves improvement in the learning efficiency compared to the benchmarks. |
|---|---|
| ISSN: | 2199-4536 2198-6053 |