This is a toy implementation of a Deep Q Network for the Cartpole problem available in Gymnasium using Pytorch. We present 2 types of network where in one we use the state vector given by the gym environment while also try to take inspiration from the Deep Q Learning with Atari paper and use image frames as state information. Please refer to the notebook and report.pdf to understand the design choices, codebase and observations regarding the set of experiments performed.
mncssj4x / deeprl-with-cartpole Goto Github PK
View Code? Open in Web Editor NEWThis is a toy implementation of a Deep Q Network for the Cartpole problem available in Gymnasium using Pytorch.