Status: Under construction.

Amca is an RL-based Backgammon agent.

This project aims to design Backgammon as a reinforcement learning problem, and gauge the performance of common deep reinforcement learning algorithms. This is done by training and gauging the performance of three popular and powerful RL algorithms:

• Deep Q Network (Mnih et. al)
• Proximal Policy Optimization (Schulman et. al)
• Soft Actor-Critic (Haarnoja et. al)
• Sarsa (Rummery and Niranjan)

The testing is done with the default parameters and implementations provided by the Stable Baselines library for all the 3 deep RL algorithms. A custom implementation heavily modified from this repo is used for SARSA, and the hyperparameters are given in the SarsaAgent object.

• play.py: to launch a game against a deep RL trained model. For example, python play.py ppo amca/models/amca.pkl will launch the model called amca.pkl that was trained using the PPO algorithm.
• train.py: to train an deep RL model (with default hyperparameters) to play. For example, python train.py -n terminator.pkl -a sac -t 1000000 will train an agent called terminator.pkl using the SAC algorithm for 1000000 steps.
• sarsa_play.py: to launch a game against a SARSA trained model. python sarsa_play.py r2d2.pkl will launch the model called r2d2.pkl that was trained using the SARSA algorithm.
• sarsa_train.py: to train a model using SARSA. For example, python sarsa_train.py jarvis.pkl -g 10000 will train an agent called jarvis.pkl using the SARSA algorithm for 10000 games.

GNU General Public License v3.0