diff --git a/a2c_sb3_cartpole.py b/a2c_sb3_cartpole.py index a76752443ce105985a35b08d86a9b38c2f639d97..e7f5770d47cc7421e7739599b5d3ed29c63da134 100644 --- a/a2c_sb3_cartpole.py +++ b/a2c_sb3_cartpole.py @@ -91,3 +91,31 @@ 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() + + + + + + + + + + + + + + + + + +