Solving Royal Game of Ur Using Reinforcement Learning
This is an incremental application of existing RL methods to a new, ancient board game domain.
The paper tackled the problem of applying reinforcement learning to the ancient Royal Game of Ur, training agents with Monte Carlo, Q-learning, and Expected Sarsa methods, with Expected Sarsa showing the fastest learning.
Reinforcement Learning has recently surfaced as a very powerful tool to solve complex problems in the domain of board games, wherein an agent is generally required to learn complex strategies and moves based on its own experiences and rewards received. While RL has outperformed existing state-of-the-art methods used for playing simple video games and popular board games, it is yet to demonstrate its capability on ancient games. Here, we solve one such problem, where we train our agents using different methods namely Monte Carlo, Qlearning and Expected Sarsa to learn optimal policy to play the strategic Royal Game of Ur. The state space for our game is complex and large, but our agents show promising results at playing the game and learning important strategic moves. Although it is hard to conclude that when trained with limited resources which algorithm performs better overall, but Expected Sarsa shows promising results when it comes to fastest learning.