Farama-Foundation · mwydmuch · Nov 7, 2025 · Nov 16, 2025 · Apr 18, 2026 · Apr 18, 2026
diff --git a/.github/workflows/linux-test.yml b/.github/workflows/linux-test.yml
@@ -15,7 +15,7 @@ jobs:
         runs-on: ubuntu-22.04
         strategy:
             matrix:
-                python-version: ['3.9', '3.10', '3.11', '3.12']
+                python-version: ['3.9', '3.10', '3.11', '3.12', '3.13', '3.14']
         steps:
             - uses: actions/checkout@v4
             - name: Set up Python ${{ matrix.python-version }}

diff --git a/.github/workflows/linux-tutorials-test.yml b/.github/workflows/linux-tutorials-test.yml
@@ -17,8 +17,8 @@ jobs:
             fail-fast: false
 
             matrix:
-                python-version: ['3.9', '3.10', '3.11', '3.12']
-                tutorial: [Tianshou, CustomEnvironment, CleanRL, SB3/connect_four, SB3/kaz, SB3/waterworld, SB3/test]  # TODO: fix tutorials and add back Ray.
+                python-version: ['3.9', '3.10', '3.11', '3.12', '3.13', '3.14']
+                tutorial: [Tianshou, CustomEnvironment, CleanRL, SB3/connect_four, SB3/kaz, SB3/test]  # TODO: fix tutorials and add back Ray.
         steps:
             - uses: actions/checkout@v4
             - name: Set up Python ${{ matrix.python-version }}

diff --git a/.github/workflows/macos-test.yml b/.github/workflows/macos-test.yml
@@ -15,7 +15,7 @@ jobs:
             matrix:
             # Big Sur, Monterey
                 os: [macos-11, macos-12]
-                python-version: ['3.9', '3.10', '3.11', '3.12']
+                python-version: ['3.9', '3.10', '3.11', '3.12', '3.13', '3.14']
         steps:
             - uses: actions/checkout@v4
             - name: Set up Python ${{ matrix.python-version }}

diff --git a/README.md b/README.md
@@ -16,7 +16,7 @@ PettingZoo includes the following families of environments:
 * [Butterfly](https://pettingzoo.farama.org/environments/butterfly): Cooperative graphical games developed by us, requiring a high degree of coordination
 * [Classic](https://pettingzoo.farama.org/environments/classic): Classical games including card games, board games, etc.
 * [MPE](https://pettingzoo.farama.org/environments/mpe): A set of simple nongraphical communication tasks, originally from https://github.com/openai/multiagent-particle-envs
-* [SISL](https://pettingzoo.farama.org/environments/sisl): 3 cooperative environments, originally from https://github.com/sisl/MADRL
+* [SISL](https://pettingzoo.farama.org/environments/sisl): 2 cooperative environments, originally from https://github.com/sisl/MADRL
 
 ## Installation
 

diff --git a/docs/_scripts/gen_envs_display.py b/docs/_scripts/gen_envs_display.py
@@ -56,7 +56,7 @@
         "simple_world_comm",
         "simple",
     ],
-    "sisl": ["multiwalker", "pursuit", "waterworld"],
+    "sisl": ["multiwalker", "pursuit"],
 }
 
 

diff --git a/docs/_static/img/aec/sisl_waterworld_aec.svg b/docs/_static/img/aec/sisl_waterworld_aec.svg
diff --git a/docs/_static/img/icons/sisl/waterworld.png b/docs/_static/img/icons/sisl/waterworld.png
diff --git a/docs/environments/sisl.md b/docs/environments/sisl.md
@@ -9,14 +9,13 @@ firstpage:
 :hidden:
 sisl/multiwalker
 sisl/pursuit
-sisl/waterworld
 ```
 
 ```{raw} html
     :file: sisl/list.html
 ```
 
-The SISL environments are a set of three cooperative multi-agent benchmark environments, created at SISL (Stanford Intelligent Systems Laboratory)) and released as part of "Cooperative multi-agent control using deep reinforcement learning." The code was originally released at: [https://github.com/sisl/MADRL](https://github.com/sisl/MADRL)
+The SISL environments are a set of three cooperative multi-agent benchmark environments, created at SISL (Stanford Intelligent Systems Laboratory) and released as part of "Cooperative multi-agent control using deep reinforcement learning." The code was originally released at: [https://github.com/sisl/MADRL](https://github.com/sisl/MADRL)
 
 ### Installation
 
@@ -26,26 +25,6 @@ The unique dependencies for this set of environments can be installed via:
 pip install 'pettingzoo[sisl]'
 ````
 
-### Usage
-To launch a [Waterworld](/environments/sisl/waterworld/) environment with random agents:
-
-```python
-from pettingzoo.sisl import waterworld_v4
-env = waterworld_v4.env(render_mode='human')
-
-env.reset()
-for agent in env.agent_iter():
-    observation, reward, termination, truncation, info = env.last()
-
-    if termination or truncation:
-        action = None
-    else:
-        action = env.action_space(agent).sample() # this is where you would insert your policy
-
-    env.step(action)
-env.close()
-```
-
 Please note that we've made major bug fixes to all environments included. As such, we discourage directly comparing results on these environments to those in the original paper.
 
 If you use these environments, please additionally cite:

diff --git a/docs/environments/sisl/sisl_waterworld.gif b/docs/environments/sisl/sisl_waterworld.gif
diff --git a/docs/tutorials/rllib/index.md b/docs/tutorials/rllib/index.md
@@ -24,12 +24,8 @@ See the [documentation](https://docs.ray.io/en/latest/rllib/index.html) for more
 ### Training:
  * [supersuit preprocessing: pistonball](https://github.com/ray-project/ray/blob/master/rllib/examples/env/greyscale_env.py)
  * [simple multi-agent: rock-paper-scissors](https://github.com/ray-project/ray/blob/master/rllib/examples/rock_paper_scissors_multiagent.py)
- * [multi-agent parameter sharing: waterworld](https://github.com/ray-project/ray/blob/master/rllib/examples/multi_agent_parameter_sharing.py)
- * [multi-agent independent learning: waterworld](https://github.com/ray-project/ray/blob/master/rllib/examples/multi_agent_independent_learning.py)
  * [multi-agent leela chess zero](https://github.com/ray-project/ray/blob/master/rllib/examples/multi-agent-leela-chess-zero.py)
 
-[//]: # (TODO: test waterworld, leela chess zero, add PR to pettingzoo if it isn't merged)
-
 ### Environments:
  * [connect four](https://github.com/ray-project/ray/blob/293fe2cb182b15499672c9cf50f79c8a9857dfb4/rllib/examples/env/pettingzoo_connect4.py)
  * [chess](https://github.com/ray-project/ray/blob/293fe2cb182b15499672c9cf50f79c8a9857dfb4/rllib/examples/env/pettingzoo_chess.py)

diff --git a/docs/tutorials/sb3/index.md b/docs/tutorials/sb3/index.md
@@ -12,8 +12,6 @@ For environments with visual observation spaces, we use a [CNN](https://stable-b
 
 For non-visual environments, we use [MLP](https://stable-baselines3.readthedocs.io/en/master/modules/ppo.html#stable_baselines3.ppo.MlpPolicy) policies and do not perform any pre-processing steps.
 
-* [PPO for Waterworld](/tutorials/sb3/waterworld/): _Train agents using PPO in a vectorized environment with discrete observations_
-
 * [Action Masked PPO for Connect Four](/tutorials/sb3/connect_four/): _Train agents using Action Masked PPO in an AEC environment_
 
 ```{eval-rst}
@@ -51,6 +49,5 @@ For more information, see the [Stable-Baselines3 v1.0 Blog Post](https://araffin
 :caption: SB3
 
 kaz
-waterworld
 connect_four
 ```
diff --git a/docs/tutorials/sb3/waterworld.md b/docs/tutorials/sb3/waterworld.md
diff --git a/pettingzoo/__init__.py b/pettingzoo/__init__.py
@@ -16,7 +16,7 @@
 
 os.environ["PYGAME_HIDE_SUPPORT_PROMPT"] = "hide"
 
-__version__ = "1.25.0"
+__version__ = "1.26.0"
 
 try:
     import sys

diff --git a/pettingzoo/sisl/all_modules.py b/pettingzoo/sisl/all_modules.py
@@ -1,7 +1,6 @@
-from pettingzoo.sisl import multiwalker_v9, pursuit_v4, waterworld_v4
+from pettingzoo.sisl import multiwalker_v9, pursuit_v4
 
 sisl_environments = {
     "sisl/multiwalker_v9": multiwalker_v9,
-    "sisl/waterworld_v4": waterworld_v4,
     "sisl/pursuit_v4": pursuit_v4,
 }
diff --git a/pettingzoo/sisl/waterworld/__init__.py b/pettingzoo/sisl/waterworld/__init__.py