NousResearch/atropos
1
0
Fork 0
mirror of https://github.com/NousResearch/atropos.git synced 2026-04-27 17:23:08 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions 1

linting

Browse source
This commit is contained in:
Shannon Sands 2025-05-10 08:44:35 +10:00
parent 06c4a9e65c
commit 9efd8c1529
2 changed files with 40 additions and 86 deletions
Download patch file Download diff file Expand all files Collapse all files

8
environments/game_environments/gymnasium/blackjack_env.py
View file

@ -11,7 +11,7 @@ Uses Monte Carlo sampling to estimate the value of the current state, similar to
import json
import logging
import random
from typing import Any, Dict, List, Optional, Tuple, Union
from typing import Any, Dict, List, Optional, Tuple
import gymnasium
import numpy as np
@ -1025,7 +1025,8 @@ class BlackjackEnv(BaseEnv):
if num_alternatives == 0:
logger.warning(
f"[_ensure_trajectory_token_limit] Step {step_idx} in MC env has no alternatives after copying. Skipping."
f"[_ensure_trajectory_token_limit] Step {step_idx} in MC env has no alternatives"
" after copying. Skipping."
)
continue
@ -1109,7 +1110,8 @@ class BlackjackEnv(BaseEnv):
working_masks = temp_new_alt_masks
max_current_tokens = max_tokens_after_this_trunc
logger.debug(
f"[_ensure_trajectory_token_limit] MC env: Step {step_idx}, after uniform pop of {min_pop_this_round}, "
f"[_ensure_trajectory_token_limit] MC env: Step {step_idx}, "
f"after uniform pop of {min_pop_this_round}, "
f"max tokens: {max_current_tokens}"
)