fix docs tictactoc dummy vector env #669 (#749)

5cat · web-flow · commit 0181fe79a591 · 2022-10-03T17:41:31.000-07:00
a fix for #669
diff --git a/docs/tutorials/tictactoe.rst b/docs/tutorials/tictactoe.rst
@@ -428,6 +428,7 @@ With the above preparation, we are close to the first learned agent. The followi
         agent_opponent: Optional[BasePolicy] = None,
     ) -> None:
         env = get_env()
+        env = DummyVectorEnv([lambda: env])
         policy, optim, agents = get_agents(
             args, agent_learn=agent_learn, agent_opponent=agent_opponent
         )

Original file line number	Diff line number	Diff line change
`@@ -428,6 +428,7 @@ With the above preparation, we are close to the first learned agent. The followi`
`428`	`428`	`agent_opponent: Optional[BasePolicy] = None,`
`429`	`429`	`) -> None:`
`430`	`430`	`env = get_env()`
	`431`	`+ env = DummyVectorEnv([lambda: env])`
`431`	`432`	`policy, optim, agents = get_agents(`
`432`	`433`	`args, agent_learn=agent_learn, agent_opponent=agent_opponent`
`433`	`434`	`)`