Merge branch 'master' into master

.github/workflows/build-docs.yml

@@ -12,36 +12,26 @@ jobs:
         env:
             SPHINX_GITHUB_CHANGELOG_TOKEN: ${{ secrets.GITHUB_TOKEN }}
         steps:
-            - uses: actions/checkout@v3
-
+            - uses: actions/checkout@v4
             - uses: actions/setup-python@v4
               with:
-                  python-version: '3.9'
-
+                  python-version: '3.11'
             - name: Install dependencies
               run: pip install -r docs/requirements.txt
-
             - name: Install PettingZoo
               run: pip install .[all]
-
             - name: Generate environment docs
               run: python docs/_scripts/gen_envs_mds.py
-
             - name: Generate environments display
               run: python docs/_scripts/gen_envs_display.py
-
             - name: Build
               run: sphinx-build -b dirhtml -v docs _build
-
             - name: Move 404
               run: mv _build/404/index.html _build/404.html
-
             - name: Update 404 links
               run: python docs/_scripts/move_404.py _build/404.html
-
             - name: Remove .doctrees
               run: rm -r _build/.doctrees
-
             - name: Upload to GitHub Pages
               uses: JamesIves/github-pages-deploy-action@v4
               with:

.github/workflows/build-publish.yml

@@ -33,9 +33,9 @@ jobs:
                       platform: manylinux_x86_64
 
         steps:
-            - uses: actions/checkout@v3
+            - uses: actions/checkout@v4
             - name: Set up Python
-              uses: actions/setup-python@v2
+              uses: actions/setup-python@v4
               with:
                   python-version: 3.x
             - name: Install dependencies

.github/workflows/docs-manual-versioning.yml

@@ -22,49 +22,37 @@ jobs:
         env:
             SPHINX_GITHUB_CHANGELOG_TOKEN: ${{ secrets.GITHUB_TOKEN }}
         steps:
-            - uses: actions/checkout@v3
+            - uses: actions/checkout@v4
               if: inputs.commit == ''
-
-            - uses: actions/checkout@v3
+            - uses: actions/checkout@v4
               if: inputs.commit != ''
               with:
                   ref: ${{ inputs.commit }}
-
             - uses: actions/setup-python@v4
               with:
-                  python-version: '3.9'
-
+                  python-version: '3.11'
             - name: Install dependencies
               run: pip install -r docs/requirements.txt
-
             - name: Install PettingZoo
               run: pip install .[all]
-
             - name: Generate environment docs
               run: python docs/_scripts/gen_envs_mds.py
-
             - name: Generate environments display
               run: python docs/_scripts/gen_envs_display.py
-
             - name: Build
               run: sphinx-build -b dirhtml -v docs _build
-
             - name: Move 404
               run: mv _build/404/index.html _build/404.html
-
             - name: Update 404 links
               run: python docs/_scripts/move_404.py _build/404.html
-
             - name: Remove .doctrees
               run: rm -r _build/.doctrees
-
             - name: Upload to GitHub Pages
               uses: JamesIves/github-pages-deploy-action@v4
               with:
                   folder: _build
                   target-folder: ${{ inputs.version }}
                   clean: false
-
             - name: Upload to GitHub Pages
               uses: JamesIves/github-pages-deploy-action@v4
               if: inputs.latest

.github/workflows/docs-test.yml

@@ -17,9 +17,9 @@ jobs:
             matrix:
                 group: [1, 2, 3, 4, 5, 6, 7, 8, 9, 10]
         steps:
-            - uses: actions/checkout@v3
+            - uses: actions/checkout@v4
             - name: Set up Python 3.11
-              uses: actions/setup-python@v3
+              uses: actions/setup-python@v4
               with:
                   python-version: '3.11'
             - name: Install dependencies

.github/workflows/docs-versioning.yml

@@ -13,42 +13,31 @@ jobs:
         env:
             SPHINX_GITHUB_CHANGELOG_TOKEN: ${{ secrets.GITHUB_TOKEN }}
         steps:
-            - uses: actions/checkout@v3
-
+            - uses: actions/checkout@v4
             - uses: actions/setup-python@v4
               with:
                   python-version: '3.9'
-
             - name: Get tag
               id: tag
               uses: dawidd6/action-get-tag@v1
               with:
                   strip_v: true
-
             - name: Install dependencies
               run: pip install -r docs/requirements.txt
-
             - name: Install PettingZoo
               run: pip install .[all]
-
             - name: Generate environment docs
               run: python docs/_scripts/gen_envs_mds.py
-
             - name: Generate environments display
               run: python docs/_scripts/gen_envs_display.py
-
             - name: Build
               run: sphinx-build -b dirhtml -v docs _build
-
             - name: Move 404
               run: mv _build/404/index.html _build/404.html
-
             - name: Update 404 links
               run: python docs/_scripts/move_404.py _build/404.html
-
             - name: Remove .doctrees
               run: rm -r _build/.doctrees
-
             - name: Upload to GitHub Pages
               uses: JamesIves/github-pages-deploy-action@v4
               with:

.github/workflows/linux-test.yml

@@ -17,9 +17,9 @@ jobs:
             matrix:
                 python-version: ['3.8', '3.9', '3.10', '3.11']
         steps:
-            - uses: actions/checkout@v3
+            - uses: actions/checkout@v4
             - name: Set up Python ${{ matrix.python-version }}
-              uses: actions/setup-python@v3
+              uses: actions/setup-python@v4
               with:
                   python-version: ${{ matrix.python-version }}
             - name: Install dependencies

.github/workflows/linux-tutorials-test.yml

@@ -19,9 +19,9 @@ jobs:
                 python-version: ['3.8', '3.9', '3.10', '3.11']
                 tutorial: [Tianshou, CustomEnvironment, CleanRL, SB3/kaz, SB3/waterworld, SB3/connect_four, SB3/test, AgileRL]  # TODO: add back Ray once next release after 2.6.2
         steps:
-            - uses: actions/checkout@v3
+            - uses: actions/checkout@v4
             - name: Set up Python ${{ matrix.python-version }}
-              uses: actions/setup-python@v3
+              uses: actions/setup-python@v4
               with:
                   python-version: ${{ matrix.python-version }}
             - name: Install dependencies and run tutorials

.github/workflows/macos-test.yml

@@ -12,11 +12,11 @@ jobs:
     macos-test:
         runs-on: macos-11
         steps:
-            - uses: actions/checkout@v3
-            - name: Set up Python 3.8
-              uses: actions/setup-python@v3
+            - uses: actions/checkout@v4
+            - name: Set up Python 3.11
+              uses: actions/setup-python@v4
               with:
-                  python-version: 3.8
+                  python-version: 3.11
             - name: Install dependencies
               run: |
                   pip install -e .[all]

.github/workflows/pre-commit.yml

@@ -12,8 +12,10 @@ jobs:
     pre-commit:
         runs-on: ubuntu-latest
         steps:
-            - uses: actions/checkout@v3
-            - uses: actions/setup-python@v3
+            - uses: actions/checkout@v4
+            - uses: actions/setup-python@v4
+              with:
+                  python-version: '3.11'
             - run: pip install pre-commit
             - run: pre-commit --version
             - run: pre-commit install

docs/content/environment_creation.md

@@ -6,7 +6,7 @@ title: Environment Creation
 This documentation overviews creating new environments and relevant useful wrappers, utilities and tests included in PettingZoo designed for the creation of new environments.
 
 
-We will walk through the creation of a simple Rock-Paper-Scissors environment, with example code for both [AEC](/api/aec/) and [Parallel](/api/aec/) environments.
+We will walk through the creation of a simple Rock-Paper-Scissors environment, with example code for both [AEC](/api/aec/) and [Parallel](/api/parallel/) environments.
 
 See our [Custom Environment Tutorial](/tutorials/custom_environment/index) for a full walkthrough on creating custom environments, including complex environment logic and illegal action masking.
 

pettingzoo/classic/connect_four/connect_four.py

@@ -283,6 +283,7 @@ def render(self):
                 )
 
         if self.render_mode == "human":
+            pygame.event.pump()
             pygame.display.update()
             self.clock.tick(self.metadata["render_fps"])
 

pettingzoo/classic/rlcard_envs/rlcard_base.py

@@ -129,9 +129,7 @@ def reset(self, seed=None, options=None):
         self.truncations = self._convert_to_dict(
             [False for _ in range(self.num_agents)]
         )
-        self.infos = self._convert_to_dict(
-            [{"legal_moves": []} for _ in range(self.num_agents)]
-        )
+        self.infos = self._convert_to_dict([{} for _ in range(self.num_agents)])
         self.next_legal_moves = list(sorted(obs["legal_actions"]))
         self._last_obs = obs["obs"]
 

pettingzoo/mpe/_mpe_utils/simple_env.py

@@ -265,6 +265,7 @@ def step(self, action):
     def enable_render(self, mode="human"):
         if not self.renderOn and mode == "human":
             self.screen = pygame.display.set_mode(self.screen.get_size())
+            self.clock = pygame.time.Clock()
             self.renderOn = True
 
     def render(self):
@@ -282,6 +283,7 @@ def render(self):
             return np.transpose(observation, axes=(1, 0, 2))
         elif self.render_mode == "human":
             pygame.display.flip()
+            self.clock.tick(self.metadata["render_fps"])
             return
 
     def draw(self):

pettingzoo/mpe/simple_reference/simple_reference.py

@@ -14,7 +14,7 @@
 | Actions            | Discrete/Continuous                              |
 | Parallel API       | Yes                                              |
 | Manual Control     | No                                               |
-| Agents             | `agents= [adversary_0, agent_0,agent_1]`         |
+| Agents             | `agents= [agent_0, agent_1]`                     |
 | Agents             | 3                                                |
 | Action Shape       | (5)                                              |
 | Action Values      | Discrete(5)/Box(0.0, 1.0, (5))                   |

pettingzoo/sisl/multiwalker/multiwalker.py

@@ -151,9 +151,11 @@ def __init__(self, *args, **kwargs):
         EzPickle.__init__(self, *args, **kwargs)
         self.env = _env(*args, **kwargs)
         self.render_mode = self.env.render_mode
-        self.agents = ["walker_" + str(r) for r in range(self.env.num_agents)]
+        self.agents = ["walker_" + str(r) for r in range(self.env.n_walkers)]
         self.possible_agents = self.agents[:]
-        self.agent_name_mapping = dict(zip(self.agents, list(range(self.num_agents))))
+        self.agent_name_mapping = dict(
+            zip(self.agents, list(range(self.env.n_walkers)))
+        )
         self._agent_selector = agent_selector(self.agents)
         # spaces
         self.action_spaces = dict(zip(self.agents, self.env.action_space))

pettingzoo/sisl/multiwalker/multiwalker_base.py

@@ -333,7 +333,6 @@ def __init__(
         self._seed()
         self.setup()
         self.screen = None
-        self.agent_list = list(range(self.n_walkers))
         self.last_rewards = [0 for _ in range(self.n_walkers)]
         self.last_dones = [False for _ in range(self.n_walkers)]
         self.last_obs = [None for _ in range(self.n_walkers)]
@@ -359,15 +358,12 @@ def setup(self):
             BipedalWalker(self.world, init_x=sx, init_y=init_y, seed=self.seed_val)
             for sx in self.start_x
         ]
-        self.num_agents = len(self.walkers)
         self.observation_space = [agent.observation_space for agent in self.walkers]
         self.action_space = [agent.action_space for agent in self.walkers]
 
         self.package_scale = self.n_walkers / 1.75
         self.package_length = PACKAGE_LENGTH / SCALE * self.package_scale
 
-        self.total_agents = self.n_walkers
-
         self.prev_shaping = np.zeros(self.n_walkers)
         self.prev_package_shaping = 0.0
 
@@ -534,7 +530,7 @@ def get_last_rewards(self):
         )
 
     def get_last_dones(self):
-        return dict(zip(self.agent_list, self.last_dones))
+        return dict(zip(list(range(self.n_walkers)), self.last_dones))
 
     def get_last_obs(self):
         return dict(
@@ -692,7 +688,8 @@ def render(self, close=False):
         self.surf = pygame.transform.flip(self.surf, False, True)
         self.screen.blit(self.surf, (-self.scroll * render_scale - offset, 0))
         if self.render_mode == "human":
-            pygame.display.flip()
+            pygame.event.pump()
+            pygame.display.update()
         elif self.render_mode == "rgb_array":
             return np.transpose(
                 np.array(pygame.surfarray.pixels3d(self.screen)), axes=(1, 0, 2)

pettingzoo/sisl/pursuit/pursuit_base.py

@@ -417,7 +417,8 @@ def render(self):
         new_observation = np.copy(observation)
         del observation
         if self.render_mode == "human":
-            pygame.display.flip()
+            pygame.event.pump()
+            pygame.display.update()
         return (
             np.transpose(new_observation, axes=(1, 0, 2))
             if self.render_mode == "rgb_array"

pettingzoo/sisl/waterworld/waterworld_base.py

@@ -741,7 +741,8 @@ def render(self):
         del observation
 
         if self.render_mode == "human":
-            pygame.display.flip()
+            pygame.event.pump()
+            pygame.display.update()
         return (
             np.transpose(new_observation, axes=(1, 0, 2))
             if self.render_mode == "rgb_array"

pettingzoo/test/parallel_test.py

@@ -49,8 +49,9 @@ def parallel_api_test(par_env: ParallelEnv, num_cycles=1000):
 
         assert isinstance(obs, dict)
         assert isinstance(infos, dict)
-        assert set(obs.keys()) == (set(par_env.agents))
-        assert set(infos.keys()) == (set(par_env.agents))
+        # Note: obs and info dicts must contain all AgentIDs, but can also have other additional keys (e.g., "common")
+        assert set(par_env.agents).issubset(set(obs.keys()))
+        assert set(par_env.agents).issubset(set(infos.keys()))
         terminated = {agent: False for agent in par_env.agents}
         truncated = {agent: False for agent in par_env.agents}
         live_agents = set(par_env.agents[:])

pettingzoo/utils/env.py

@@ -182,7 +182,7 @@ def last(
     ) -> tuple[ObsType | None, float, bool, bool, dict[str, Any]]:
         """Returns observation, cumulative reward, terminated, truncated, info for the current agent (specified by self.agent_selection)."""
         agent = self.agent_selection
-        assert agent
+        assert agent is not None
         observation = self.observe(agent) if observe else None
         return (
             observation,

pettingzoo/utils/wrappers/__init__.py

@@ -3,5 +3,7 @@
 from pettingzoo.utils.wrappers.base_parallel import BaseParallelWrapper
 from pettingzoo.utils.wrappers.capture_stdout import CaptureStdoutWrapper
 from pettingzoo.utils.wrappers.clip_out_of_bounds import ClipOutOfBoundsWrapper
+from pettingzoo.utils.wrappers.multi_episode_env import MultiEpisodeEnv
+from pettingzoo.utils.wrappers.multi_episode_parallel_env import MultiEpisodeParallelEnv
 from pettingzoo.utils.wrappers.order_enforcing import OrderEnforcingWrapper
 from pettingzoo.utils.wrappers.terminate_illegal import TerminateIllegalWrapper