diff --git a/reinforce_cartpole.py b/reinforce_cartpole.py index a76752443ce105985a35b08d86a9b38c2f639d97..9c54b7efdb3ecbf45a2670db2c215f0b28356e8c 100644 --- a/reinforce_cartpole.py +++ b/reinforce_cartpole.py @@ -7,14 +7,6 @@ from torch.distributions import Categorical import matplotlib.pyplot as plt - - - - - - - - # Create the environment env = gym.make("CartPole-v1", render_mode="human") @@ -91,3 +83,10 @@ for i in range(500): env.close() + +# Plot the policy loss against iterations +plt.plot([i for i in range(0,500)],episodes_rewards) +plt.xlabel('Iterations') +plt.ylabel('Policy Loss') +plt.title('Policy Loss vs. Iterations') +plt.show()