Update README.md
Browse files
README.md
CHANGED
@@ -24,4 +24,6 @@ model-index:
|
|
24 |
This is a custom agent. Performance has been measured over 900 episodes.
|
25 |
To try the agent, user needs to import the ParameterisedPolicy class from the Agent_class.py file. </br>
|
26 |
Training progress:
|
27 |
-
![training](training_graph.jpg)
|
|
|
|
|
|
24 |
This is a custom agent. Performance has been measured over 900 episodes.
|
25 |
To try the agent, user needs to import the ParameterisedPolicy class from the Agent_class.py file. </br>
|
26 |
Training progress:
|
27 |
+
![training](training_graph.jpg)
|
28 |
+
|
29 |
+
Numbers on X axis are average over 40 episodes, each lasting for about 500 episodes on average. So in total the agent was trained over about 5e6 timesteps.
|