update

Author: hsvgbkhgbv

README.md

@@ -172,8 +172,10 @@ The simple use of the environment is shown as the following codes.
 state, global_state = env.reset()
 
 for t in range(240):
-    actions = agents.get_actions() # a vector involving all agents' actions
+    actions = agents.get_actions(state) # a vector involving all agents' actions
     reward, done, info = env.step(actions)
+    next_state = trainer.env.get_obs()
+    state = next_state
 ```
 
 <br />