Bump TicTacToe environment to version 4

Farama-Foundation · Mar 20, 2024 · 72ef62f · 72ef62f
1 parent f750754
commit 72ef62f
Show file tree

Hide file tree

Showing 10 changed files with 18 additions and 18 deletions.
diff --git a/docs/api/wrappers/pz_wrappers.md b/docs/api/wrappers/pz_wrappers.md
@@ -65,8 +65,8 @@ You can apply these wrappers to your environment in a similar manner to the belo
 To wrap an AEC environment:
 ```python
 from pettingzoo.utils import TerminateIllegalWrapper
-from pettingzoo.classic import tictactoe_v3
-env = tictactoe_v3.env()
+from pettingzoo.classic import tictactoe_v4
+env = tictactoe_v4.env()
 env = TerminateIllegalWrapper(env, illegal_reward=-1)
 
 env.reset()

diff --git a/pettingzoo/classic/all_modules.py b/pettingzoo/classic/all_modules.py
@@ -8,14 +8,14 @@
     rps_v2,
     texas_holdem_no_limit_v6,
     texas_holdem_v4,
-    tictactoe_v3,
+    tictactoe_v4,
 )
 
 classic_environments = {
     "classic/chess_v6": chess_v6,
     "classic/rps_v2": rps_v2,
     "classic/connect_four_v3": connect_four_v3,
-    "classic/tictactoe_v3": tictactoe_v3,
+    "classic/tictactoe_v4": tictactoe_v4,
     "classic/leduc_holdem_v4": leduc_holdem_v4,
     "classic/texas_holdem_v4": texas_holdem_v4,
     "classic/texas_holdem_no_limit_v6": texas_holdem_no_limit_v6,

diff --git a/pettingzoo/classic/tictactoe/tictactoe.py b/pettingzoo/classic/tictactoe/tictactoe.py
@@ -9,7 +9,7 @@
 
 This environment is part of the <a href='..'>classic environments</a>. Please read that page first for general information.
 
-| Import             | `from pettingzoo.classic import tictactoe_v3` |
+| Import             | `from pettingzoo.classic import tictactoe_v4` |
 |--------------------|-----------------------------------------------|
 | Actions            | Discrete                                      |
 | Parallel API       | Yes                                           |
@@ -112,7 +112,7 @@ def env(**kwargs):
 class raw_env(AECEnv, EzPickle):
     metadata = {
         "render_modes": ["human", "rgb_array"],
-        "name": "tictactoe_v3",
+        "name": "tictactoe_v4",
         "is_parallelizable": False,
         "render_fps": 1,
     }

diff --git a/pettingzoo/classic/tictactoe_v3.py → pettingzoo/classic/tictactoe_v4.py b/pettingzoo/classic/tictactoe_v3.py → pettingzoo/classic/tictactoe_v4.py
diff --git a/pettingzoo/test/api_test.py b/pettingzoo/test/api_test.py
@@ -73,7 +73,7 @@ def action_mask():
     "go_v5",
     "chess_v6",
     "connect_four_v3",
-    "tictactoe_v3",
+    "tictactoe_v4",
     "gin_rummy_v4",
 ]
 env_graphical_obs = ["knights_archers_zombies_v10"]
@@ -96,7 +96,7 @@ def action_mask():
     "knights_archers_zombies_v10",
     "chess_v6",
     "connect_four_v3",
-    "tictactoe_v3",
+    "tictactoe_v4",
     "gin_rummy_v4",
 ]
 env_diff_agent_obs_size = [

diff --git a/test/all_parameter_combs_test.py b/test/all_parameter_combs_test.py
@@ -43,7 +43,7 @@
     rps_v2,
     texas_holdem_no_limit_v6,
     texas_holdem_v4,
-    tictactoe_v3,
+    tictactoe_v4,
 )
 from pettingzoo.mpe import (
     simple_adversary_v3,
@@ -104,7 +104,7 @@
     ["classic/connect_four_v3", connect_four_v3, dict()],
     ["classic/rps_v2", rps_v2, dict()],
     ["classic/chess_v6", chess_v6, dict()],
-    ["classic/tictactoe_v3", tictactoe_v3, dict()],
+    ["classic/tictactoe_v4", tictactoe_v4, dict()],
     ["classic/gin_rummy_v4", gin_rummy_v4, dict()],
     ["classic/gin_rummy_v4", gin_rummy_v4, dict(opponents_hand_visible=True)],
     ["mpe/simple_v3", simple_v3, dict(max_cycles=50)],

diff --git a/tutorials/LangChain/langchain_example.py b/tutorials/LangChain/langchain_example.py
@@ -37,9 +37,9 @@ def rock_paper_scissors():
 
 
 def tic_tac_toe():
-    from pettingzoo.classic import tictactoe_v3
+    from pettingzoo.classic import tictactoe_v4
 
-    env = tictactoe_v3.env(render_mode="human")
+    env = tictactoe_v4.env(render_mode="human")
     agents = {
         name: ActionMaskAgent(name=name, model=ChatOpenAI(temperature=0.2), env=env)
         for name in env.possible_agents

diff --git a/tutorials/SB3/test/test_sb3_action_mask.py b/tutorials/SB3/test/test_sb3_action_mask.py
@@ -10,7 +10,7 @@
     leduc_holdem_v4,
     texas_holdem_no_limit_v6,
     texas_holdem_v4,
-    tictactoe_v3,
+    tictactoe_v4,
 )
 
 pytest.importorskip("stable_baselines3")
@@ -30,7 +30,7 @@
 MEDIUM_ENVS = [
     leduc_holdem_v4,  # with 10x as many steps it gets higher total rewards (9 vs -9), 0.52 winrate, and 0.92 vs 0.83 total scores
     hanabi_v5,  # even with 10x as many steps, total score seems to always be tied between the two agents
-    tictactoe_v3,  # even with 10x as many steps, agent still loses every time (most likely an error somewhere)
+    tictactoe_v4,  # even with 10x as many steps, agent still loses every time (most likely an error somewhere)
     chess_v6,  # difficult to train because games take so long, performance varies heavily
 ]
 

diff --git a/tutorials/Tianshou/2_training_agents.py b/tutorials/Tianshou/2_training_agents.py
@@ -22,7 +22,7 @@
 from tianshou.trainer import offpolicy_trainer
 from tianshou.utils.net.common import Net
 
-from pettingzoo.classic import tictactoe_v3
+from pettingzoo.classic import tictactoe_v4
 
 
 def _get_agents(
@@ -64,7 +64,7 @@ def _get_agents(
 
 def _get_env():
     """This function is needed to provide callables for DummyVectorEnv."""
-    return PettingZooEnv(tictactoe_v3.env())
+    return PettingZooEnv(tictactoe_v4.env())
 
 
 if __name__ == "__main__":

diff --git a/tutorials/Tianshou/3_cli_and_logging.py b/tutorials/Tianshou/3_cli_and_logging.py
@@ -26,7 +26,7 @@
 from tianshou.utils.net.common import Net
 from torch.utils.tensorboard import SummaryWriter
 
-from pettingzoo.classic import tictactoe_v3
+from pettingzoo.classic import tictactoe_v4
 
 
 def get_parser() -> argparse.ArgumentParser:
@@ -146,7 +146,7 @@ def get_agents(
 
 
 def get_env(render_mode=None):
-    return PettingZooEnv(tictactoe_v3.env(render_mode=render_mode))
+    return PettingZooEnv(tictactoe_v4.env(render_mode=render_mode))
 
 
 def train_agent(