acsicuib/DQNMario

DQN Approach for Distributed Service Placement on MARIO approach

DQNMario

Tasks Prototype 1

• Insert Learning Model in Agent
• Assign a simple Reward model
• Testing

Install dependencies

TODO

• torch https://pytorch.org/

• torch geometry https://pytorch-geometric.readthedocs.io/en/latest/notes/installation.html

• tensorboard

  pip install tensorflow tensorboard

  tensorboard --logdir tmp/tensorlogs/

References:

• https://deeplearning.neuromatch.io/tutorials/W3D2_BasicReinforcementLearning/student/W3D2_Tutorial1.html
• https://deeplearning.neuromatch.io/tutorials/W3D3_ReinforcementLearningForGames/student/W3D3_Tutorial1.html
• https://github.com/xkiwilabs/DQN-using-PyTorch-and-ML-Agents
• https://github.com/Beshario/DRL-Robotics-Arm/blob/516b0cac91452a28d4cd91d698ab4a5d323e13b5/python/DQN.py#L419
• https://github.com/cpnota/autonomous-learning-library/blob/aaa5403ead52f1175b460fc3984864355c575061/all/experiments/single_env_experiment.py
• https://github.com/openai/gym
• https://pytorch-geometric.readthedocs.io/en/latest/notes/create_dataset.html