cartpole-dqn-pytorch
PublicAI Agent learn to sole the cart and pole environment in the OpenAI gym. The agent is built using deep-q-network to approximate the q-values of state-action pair.
deep-learningdeep-q-learningdeep-q-networkdeep-reinforcement-learningdqn-pytorchpythonpytorchq-learningreinforcement-learningreinforcement-learning-agent
Creat：2022-02-24T20:57:46
Update：2022-03-08T04:05:55
0
Stars
0
Stars Increase