79107096

Date: 2024-10-20 13:10:10
Score: 1
Natty:
Report link

If you print out the function env.step(action) then you'll see that you get 5 values

this is an example of the frozen lake environment:

(1, 0.0, False, False, {'prob': 0.3333333333333333})

So we have (new_sate,reward,done,truncated,info), just make sure to add "truncated" which by they way is a boolean since it indicates if the truncation condition has been satisfied outside of the MDP.

Hope this helps and here is a link that can help you understand these values further

Reasons:
  • Whitelisted phrase (-1): Hope this helps
  • No code block (0.5):
  • Filler text (0.5): 3333333333333333
  • Low reputation (1):
Posted by: 8b1t_gh05t