- Comparing the algorithm performance with other baseline techniques for OpenAI game environment
- Exploring performance based on input data preprocessing , using different Neural Network architectures & CPU vs GPU training
- Modifying different hyperparameters to analyze their impact on the overall performance of the algorithm
-
The model is developed using TensorFlow and input data is collected from OpenAI GYM's MS-PACMAN environment.
-
Performance of different neural network architectures is explored:
-
GPU based training was done using Google Collaboratory
-
Reference : OpenAI GYM Baselines
- Different models based on the modified hyperparemeters, CPU training & GPU training.
- Performance comparison(rewards & loss function) plots.