Multiplayer AlphaZero
This work addresses multiplayer environments, such as equity trading, but is incremental as it adapts an existing method to new scenarios.
The authors tackled the problem of extending AlphaZero to multiplayer games, demonstrating that their modified algorithm successfully learns and consistently outperforms Monte Carlo tree search in two simple 3-player games.
The AlphaZero algorithm has achieved superhuman performance in two-player, deterministic, zero-sum games where perfect information of the game state is available. This success has been demonstrated in Chess, Shogi, and Go where learning occurs solely through self-play. Many real-world applications (e.g., equity trading) require the consideration of a multiplayer environment. In this work, we suggest novel modifications of the AlphaZero algorithm to support multiplayer environments, and evaluate the approach in two simple 3-player games. Our experiments show that multiplayer AlphaZero learns successfully and consistently outperforms a competing approach: Monte Carlo tree search. These results suggest that our modified AlphaZero can learn effective strategies in multiplayer game scenarios. Our work supports the use of AlphaZero in multiplayer games and suggests future research for more complex environments.