Human-level control using Deep Reinforcement Learning (deep Q learning) in OpenAI's gym cartpole environment with pytorch
- A simple implementation of the paper "Human-level control through deep reinforcement learning" from DeepMind in python, using Pytorch framework.
- to train the agent and the deep Q network run
train.py. - the parameters of the Q neural network and the agent could be set directly in
train.py. - models and result plots are saved in the corresponding directories.
- link to paper:
https://www.nature.com/articles/nature14236
https://www.researchgate.net/publication/272837232_Human-level_control_through_deep_reinforcement_learning