Simple implementations of reinforcement learning algorithms on the CartPole-v1 environment.
Implementation of the DQN algorithm using experience replay buffer and a seperate target network in the OpenAI Gym's CartPole-v1 environment. Accompanying blog article about the algorithm and some of the experiments I did with it can be found here.
-
Tensorflow 2.2.0
-
OpenAI Gym
-
Numpy
-
Pandas