we got the code for the enviroment from https://github.com/YuriyGuts/snake-ai-reinforcement we highly modified utils/memory.py, agent/dqn.py and train.py to implement DDQN, SARSA, multistep, priorized replay and dueling network. we also created a logging system and made changes to the gameplay and enviroment we did hyperparametersearch mostly for the memory size of experience replay, stepsize of multistep and different decays of the exploration rate
AI for Snake game trained from pixels using Deep Reinforcement Learning (DQN).
Contains the tools for training and observing the behavior of the agents, either in CLI or GUI mode.
All components have been written in Python 3.6. Training on GPU is supported but disabled by default. If you have CUDA and would like to use a GPU, use the GPU version of TensorFlow by changing tensorflow to tensorflow-gpu in the requirements file.
To install all Python dependencies, run:
$ make deps
You can find a few pre-trained DQN agents on the Releases page. Pass the model file to the play.py front-end script (see play.py -h for help).
-
dqn-10x10-blank.modelAn agent pre-trained on a blank 10x10 level (
snakeai/levels/10x10-blank.json). -
dqn-10x10-obstacles.modelAn agent pre-trained on a 10x10 level with obstacles (
snakeai/levels/10x10-obstacles.json).
To train an agent using the default configuration, run:
$ make train
The trained model will be checkpointed during the training and saved as dqn-final.model afterwards.
Run train.py with custom arguments to change the level or the duration of the training (see train.py -h for help).
The behavior of the agent can be tested either in batch CLI mode where the agent plays a set of episodes and outputs summary statistics, or in GUI mode where you can see each individual step and action.
To test the agent in batch CLI mode, run the following command and check the generated .csv file:
$ make play
To use the GUI mode, run:
$ make play-gui
To play on your own using the arrow keys (I know you want to), run:
$ make play-human
$ make test