Deep reinforcement learning policy in Hex game system
| Autor: | Xuejun Li, Mengxuan Lu |
|---|---|
| Rok vydání: | 2018 |
| Předmět: |
Artificial neural network
Computer science business.industry ComputingMilieux_PERSONALCOMPUTING 020206 networking & telecommunications 02 engineering and technology Space (commercial competition) Zero (linguistics) 020210 optoelectronics & photonics Value network Asynchronous communication 0202 electrical engineering electronic engineering information engineering Reinforcement learning Artificial intelligence business |
| Zdroj: | 2018 Chinese Control And Decision Conference (CCDC). |
| DOI: | 10.1109/ccdc.2018.8408296 |
| Popis: | Hex game is a zero-sum chess game. It has a large solution space when using 11×11 size of chess board. In recent years, deep reinforcement learning-based Go game systems, i.e. AlphaGo and AlphaGo Zero, have gotten huge achievement. In this paper, we design the self-learning method and system structure of Hex game, design policy network and value network referred to residual network, and use asynchronous advantage actor-critic algorithm to train policy network and value network. The comparison of deep reinforcement learning-based policy network and fixed strategy proves better effect of self-learning. |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|