Update README.md

README.md

@@ -26,4 +26,6 @@ To try the agent, user needs to import the ParameterisedPolicy class from the Ag
 Training progress:
 ![training](training_graph.jpg)
 
-Numbers on X axis are average over 40 episodes, each lasting for about 500 timesteps on average. So in total the agent was trained over about 5e6 timesteps.
+Numbers on X axis are average over 40 episodes, each lasting for about 500 timesteps on average. So in total the agent was trained over about 5e6 timesteps.
+Learning rate decay schedule: <code>torch.optim.lr_scheduler.StepLR(opt, step_size=4000, gamma=0.7)</code>
+