Skip to main content

Deep Q-Network (DQN) Experiments

Here we can observe three experiments with DQN RL algorithm (with different number of timesteps {2000,5000,10000}) seperately (with non-smoothing form) and finally all three together (with smoothing form).
Created on February 28|Last edited on May 5

Experiment with 2.000 timesteps


02004006008001kEpisode-2000200400600800Reward
Run set
142


Experiment with 5.000 timesteps


Run set
142


Experiment with 10.000 timesteps


Run set
142


Final chart with all experiments


Run set
135



Specs of Experiments


Run set
142