set timelimit wrapper's max_episode_step to 5100

zbeucler2018 · zbeucler2018 · commit 0bd9153434a6 · 2023-11-25T19:54:08.000-05:00
diff --git a/train.py b/train.py
@@ -34,7 +34,7 @@ def make_env():
             crash_reward=config.crash_reward,
             wall_crash_reward=config.wall_crash_reward,
             use_deepmind_wrapper=True,
-            max_episode_steps=5_1000
+            max_episode_steps=5_100
         )
         return env
 

Original file line number	Diff line number	Diff line change
`@@ -34,7 +34,7 @@ def make_env():`
`34`	`34`	`crash_reward=config.crash_reward,`
`35`	`35`	`wall_crash_reward=config.wall_crash_reward,`
`36`	`36`	`use_deepmind_wrapper=True,`
`37`		`- max_episode_steps=5_1000`
	`37`	`+ max_episode_steps=5_100`
`38`	`38`	`)`
`39`	`39`	`return env`
`40`	`40`