A pole is attached by an un-actuated joint to a cart, which moves along a frictionless track. The pendulum starts upright, and the goal is to prevent it from falling over by increasing and reducing the cart's velocity.
The agent only knows his cart position, cart velocity, pole angle, and pole velocity in evry step. The agent can take one action from push left and push right.
Following are the commands used to train and test the model:
To train the model:
python dqn.py train --itr 200 --capacity 10000 --batch 80 --save True --plot TrueTo run with pre-trained weights:
python dqn.py testReward Plot:
The obtained result:
