Novel reinforcement learning model by tiled neural network based on the cortico-basal ganglia circuit
-
- KITA Tetsuji
- Ritsumeikan University
-
- ONOI Shunya
- Ritsumeikan University
-
- TAKEHARA Ryo
- Ritsumeikan University
-
- HIROKANE Kojiro
- Ritsumeikan University Osaka University
-
- KITSUKAWA Takashi
- Ritsumeikan University
Bibliographic Information
- Other Title
-
- 大脳皮質-大脳基底核回路を模したタイリング型ネットワークによる強化学習モデル
Abstract
<p>Artificial reinforcement learning algorithms have evolved in the direction of practicality, many of which take advantage of reward prediction errors. Animals also can perform reinforcement learning, which means that animals have neural circuits engaged in the reinforcement learning. In fact, dopamine neurons in the substantia nigra were found to represent the reward prediction error suggesting that neural circuits in the basal ganglia, which are the targets of the dopamine neurons, may be involved in the information processing related to the reinforcement learning. However, it remains to reveal reinforcement learning algorithms at the neural circuit level. In this study, we constructed a neural network model for reinforcement learning by parallelly tiling of neural circuits of the cortex-basal ganglia using reward prediction errors from dopamine neurons. We compared our model to the conventional TD learning using Markov decision process tasks, Maze and CartPole. As a result, we found that our model reproduced the activity patterns of dopamine neurons as observed in animals performing reinforcement learning, and demonstrated performance comparable to that of TD learning.</p>
Journal
-
- Proceedings of the Annual Conference of JSAI
-
Proceedings of the Annual Conference of JSAI JSAI2023 (0), 3Xin426-3Xin426, 2023
The Japanese Society for Artificial Intelligence
- Tweet
Details 詳細情報について
-
- CRID
- 1390015333244682240
-
- ISSN
- 27587347
-
- Text Lang
- ja
-
- Data Source
-
- JaLC
-
- Abstract License Flag
- Disallowed