Modular implementation of DQN algorithm.
- Python 2.7 or 3.5
- TensorFlow 1.10
- gym
- numpy
- tqdm progress-bar
- Using a neural network based as the function approximator for Q-learning
- Using a target network and soft-update to synchronoze target network with Q-network
- Using gradient clipping to make small but consistent updates towards optimal Q-network
- Implementation of Tabular Q-learning
To train a model for Cartpole-v0:
$ python test_graph_dqn.py
To view the tensorboard
$tensorboard --logdir .