Exploring Deep Reinforcement Learning Models
School Project
As
part of a school project, I delved
into the fascinating world of Deep
Q-Learning, experimenting with
various models, including DQN (Deep
Q-Network) and DDPG (Deep
Deterministic Policy Gradient).
My focus was on optimizing
hyperparameters within the Pendulum
v1 gym environment, where I analyzed
the effects of different
configurations on the agent's
performance.
This hands-on
experience not only deepened my
understanding of reinforcement
learning algorithms but also honed
my skills in model tuning and
performance evaluation, making it a
rewarding learning journey. I am
proud to have attained distinctions
for this module overall