paper-with-me

Papers

Three-Head Neural Network Architecture for AlphaZero Learning

2019-09-25 · Chao GAO, Martin Mueller, Ryan Hayward, Hengshuai Yao, Shangling Jui

The search-based reinforcement learning algorithm AlphaZero has been used as a general method for mastering two-player games Go, chess and Shogi. One crucial ingredient in AlphaZero (and its predecessor AlphaGo Zero) is the two-head network architecture that outputs two estimates --- policy and value --- for one input game state. The merit of such an architecture is that letting policy and value learning share the same representation substantially improved generalization of the neural net. A three-head network architecture has been recently proposed that can learn a third action-value head on a fixed dataset the same as for two-head net. Also, using the action-value head in Monte Carlo tree search (MCTS) improved the search efficiency. However, effectiveness of the three-head network has not been investigated in an AlphaZero style learning paradigm. In this paper, using the game of Hex as a test domain, we conduct an empirical study of the three-head network architecture in AlpahZero learning. We show that the architecture is also advantageous at the zero-style iterative learning. Specifically, we find that three-head network can induce the following benefits: (1) learning can become faster as search takes advantage of the additional action-value head; (2) better prediction results than two-head architecture can be achieved when using additional action-value learning as an auxiliary task.

📄 PDF Abstract BibTeX

Code (0)

등록된 구현이 없습니다.

Similar Papers 제목 키워드 기반

Reproducing AlphaZero on Tablut: Self-Play RL for an Asymmetric Board Game

2026-04-07 · Tõnis Lees, Tambet Matiisen arxiv

This work investigates the adaptation of the AlphaZero reinforcement learning algorithm to Tablut, an asymmetric historical board game featuring unequal piece counts and distinct player objectives (king capture versus ki…

Reinforcement LearningData Augmentation

Warm-Start AlphaZero Self-Play Search Enhancements

2020-04-26 · Hui Wang, Mike Preuss, Aske Plaat

Recently, AlphaZero has achieved landmark results in deep reinforcement learning, by providing a single self-play architecture that learned three different games at super human level. AlphaZero is a large and complicated…

Board GamesDeep Reinforcement LearningEvolutionary AlgorithmsReinforcement Learning

Train on Small, Play the Large: Scaling Up Board Games with AlphaZero and GNN

2021-07-18 · Shai Ben-Assayag, Ran El-Yaniv

Playing board games is considered a major challenge for both humans and AI researchers. Because some complicated board games are quite hard to learn, humans usually begin with playing on smaller boards and incrementally …

Board GamesGraph Neural NetworkIncremental Learning

Targeted Search Control in AlphaZero for Effective Policy Improvement

2023-02-23 · Alexandre Trudeau, Michael Bowling

AlphaZero is a self-play reinforcement learning algorithm that achieves superhuman play in chess, shogi, and Go via policy iteration. To be an effective policy improvement operator, AlphaZero's search requires accurate v…

AlphaZero-Inspired Game Learning: Faster Training by Using MCTS Only at Test Time

2022-04-28 · Johannes Scheiermann, Wolfgang Konen

Recently, the seminal algorithms AlphaGo and AlphaZero have started a new era in game learning and deep reinforcement learning. While the achievements of AlphaGo and AlphaZero - playing Go and other complex games at supe…

Deep Reinforcement LearningGPURubik's Cube