Upload inference.py

inference.py

@@ -61,7 +61,7 @@ async def main():
     state = await env.reset()
     
     try:
-        for step in range(1, 21): 
+        for step in range(1, 201): 
             action_int, action_text = await get_action_from_llama(state)
             state, reward, done = await env.step(action_int)
             log_step(step=step, action=str(action_int), reward=reward, done=done)