bumped kaz, prison, battlfield versions

docs/_includes/services.html

@@ -30,8 +30,8 @@ <h4 class="service-heading">{{ service.title | markdownify }}</h4>
         <div class="service-code">
           <pre>
             <code>
-  from pettingzoo.butterfly import knights_archers_zombies_v8
-  env = knights_archers_zombies_v8.env()
+  from pettingzoo.butterfly import knights_archers_zombies_v9
+  env = knights_archers_zombies_v9.env()
   env.reset()
   for agent in env.agent_iter():
       observation, reward, done, info = env.last()

docs/api.md

@@ -179,8 +179,8 @@ Where `max_episodes` and `max_steps` both limit the total number of evaluations
 Often, you want to be able to play before trying to learn it to get a better feel for it. Some of our games directly support this:
 
 ``` python
-from pettingzoo.butterfly import prison_v3
-prison_v3.manual_control(<environment parameters>)
+from pettingzoo.butterfly import prison_v4
+prison_v4.manual_control(<environment parameters>)
 ```
 
 Environments say if they support this functionality in their documentation, and what the specific controls are.
@@ -201,12 +201,12 @@ Some games support this via:
 
 ``` python
 import time
-from pettingzoo.butterfly import knights_archers_zombies_v8
+from pettingzoo.butterfly import knights_archers_zombies_v9
 
-env = knights_archers_zombies_v8.env()
+env = knights_archers_zombies_v9.env()
 env.reset()
 
-manual_policy = knights_archers_zombies_v8.ManualPolicy(env)
+manual_policy = knights_archers_zombies_v9.ManualPolicy(env)
 
 for agent in env.agent_iter():
     observation, reward, done, info = env.last()

docs/butterfly/knights_archers_zombies.md

@@ -11,7 +11,7 @@ observation-values: "(0, 255)"
 state-shape: "(720, 1280, 3)"
 state-values: "(0, 255)"
 average-total-reward: "2.95"
-import: "from pettingzoo.butterfly import knights_archers_zombies_v8"
+import: "from pettingzoo.butterfly import knights_archers_zombies_v9"
 agent-labels: "agents= ['archer_0', 'archer_1', 'knight_0', 'knight_1']"
 ---
 
@@ -43,7 +43,7 @@ Press 'M' key to spawn a new knight.
 ### Arguments
 
 ``` python
-knights_archers_zombies_v8.env(spawn_rate=20, num_knights=2, num_archers=2,
+knights_archers_zombies_v9.env(spawn_rate=20, num_knights=2, num_archers=2,
 killable_knights=True, killable_archers=True, line_death=True, pad_observation=True,
 max_cycles=900)
 ```
@@ -66,6 +66,7 @@ max_cycles=900)
 
 ### Version History
 
+* v9: Code rewrite and numerous fixes (1.16.0)
 * v8: Code cleanup and several bug fixes (1.14.0)
 * v7: Minor bug fix relating to end of episode crash (1.6.0)
 * v6: Fixed reward structure (1.5.2)

docs/butterfly/prison.md

@@ -10,7 +10,7 @@ observation-values: "(0, 255) or (-300, 300)"
 state-shape: "(650, 750, 3)"
 state-values: "(0, 255)"
 average-total-reward: "2.77"
-import: "from pettingzoo.butterfly import prison_v3"
+import: "from pettingzoo.butterfly import prison_v4"
 agent-labels: "agents= ['prisoner_0', 'prisoner_1', ..., 'prisoner_7']"
 ---
 
@@ -39,7 +39,7 @@ Select different aliens with 'W', 'A', 'S' or 'D'. Move the selected alien left
 ### Arguments
 
 ``` python
-prison_v3.env(vector_observation=False, continuous=False, synchronized_start=False,
+prison_v4.env(vector_observation=False, continuous=False, synchronized_start=False,
 identical_aliens=False, max_cycles=150, num_floors=4, random_aliens=False)
 ```
 
@@ -61,8 +61,9 @@ identical_aliens=False, max_cycles=150, num_floors=4, random_aliens=False)
 
 ### Version History
 
+* v4: Fixed state() space (1.16.0)
 * v3: Changed default argument for `max_cycles`  (1.6.0)
 * v2: Misc fixes, bumped PyGame and PyMunk version (1.4.0)
 * v1: Fix to continuous mode (1.0.1)
 * v0: Initial versions release (1.0.0)
-</div>
+</div>

docs/magent/battlefield.md

@@ -9,7 +9,7 @@ observation-shape: "(13,13,5)"
 observation-values: "[0,2]"
 state-shape: "(80, 80, 5)"
 state-values: "(0, 2)"
-import: "from pettingzoo.magent import battlefield_v3"
+import: "from pettingzoo.magent import battlefield_v4"
 agent-labels: "agents= [red_[0-11], blue_[0-11]]"
 ---
 

pettingzoo/butterfly/knights_archers_zombies/knights_archers_zombies.py

@@ -36,7 +36,7 @@ class raw_env(AECEnv, EzPickle):
 
     metadata = {
         "render.modes": ["human", "rgb_array"],
-        "name": "knights_archers_zombies_v8",
+        "name": "knights_archers_zombies_v9",
         "is_parallelizable": True,
         "video.frames_per_second": const.FPS,
     }

pettingzoo/butterfly/knights_archers_zombies/manual_policy.py

@@ -50,14 +50,14 @@ def available_agents(self):
 
 
 if __name__ == "__main__":
-    from pettingzoo.butterfly import knights_archers_zombies_v8
+    from pettingzoo.butterfly import knights_archers_zombies_v9
 
     clock = pygame.time.Clock()
 
-    env = knights_archers_zombies_v8.env()
+    env = knights_archers_zombies_v9.env()
     env.reset()
 
-    manual_policy = knights_archers_zombies_v8.ManualPolicy(env)
+    manual_policy = knights_archers_zombies_v9.ManualPolicy(env)
 
     for agent in env.agent_iter():
         clock.tick(env.metadata['video.frames_per_second'])

pettingzoo/butterfly/prison/prison.py

@@ -102,7 +102,7 @@ def __init__(self, continuous=False, vector_observation=False, max_cycles=150, n
         self.sprite_img_heights = [40, 40, 46, 48, 32, 54, 48, 53]
         self.metadata = {
             'render.modes': ['human', "rgb_array"],
-            'name': "prison_v3",
+            'name': "prison_v4",
             'is_parallelizable': True,
             'video.frames_per_second': FPS,
         }

pettingzoo/magent/battlefield_v3.py → pettingzoo/magent/battlefield_v4.py

@@ -35,7 +35,7 @@ def raw_env(map_size=default_map_size, max_cycles=max_cycles_default, minimap_mo
 class _parallel_env(magent_parallel_env, EzPickle):
     metadata = {
         "render.modes": ["human", "rgb_array"],
-        'name': "battlefield_v3",
+        'name': "battlefield_v4",
         "video.frames_per_second": 5,
     }
 

test/all_modules.py

@@ -39,18 +39,18 @@
 from pettingzoo.classic import hanabi_v4
 from pettingzoo.classic import backgammon_v3
 
-from pettingzoo.butterfly import knights_archers_zombies_v8
+from pettingzoo.butterfly import knights_archers_zombies_v9
 from pettingzoo.butterfly import pistonball_v6
 from pettingzoo.butterfly import cooperative_pong_v5
-from pettingzoo.butterfly import prison_v3
+from pettingzoo.butterfly import prison_v4
 from pettingzoo.butterfly import prospector_v4
 
 from pettingzoo.magent import battle_v3
 from pettingzoo.magent import adversarial_pursuit_v3
 from pettingzoo.magent import gather_v4
 from pettingzoo.magent import combined_arms_v5
 from pettingzoo.magent import tiger_deer_v3
-from pettingzoo.magent import battlefield_v3
+from pettingzoo.magent import battlefield_v4
 
 from pettingzoo.mpe import simple_adversary_v2
 from pettingzoo.mpe import simple_crypto_v2
@@ -119,15 +119,15 @@
     "classic/hanabi_v4": hanabi_v4,
     "classic/backgammon_v3": backgammon_v3,
 
-    "butterfly/knights_archers_zombies_v8": knights_archers_zombies_v8,
+    "butterfly/knights_archers_zombies_v9": knights_archers_zombies_v9,
     "butterfly/pistonball_v6": pistonball_v6,
     "butterfly/cooperative_pong_v5": cooperative_pong_v5,
-    "butterfly/prison_v3": prison_v3,
+    "butterfly/prison_v4": prison_v4,
     "butterfly/prospector_v4": prospector_v4,
 
     "magent/adversarial_pursuit_v3": adversarial_pursuit_v3,
     "magent/battle_v3": battle_v3,
-    "magent/battlefield_v3": battlefield_v3,
+    "magent/battlefield_v4": battlefield_v4,
     "magent/combined_arms_v5": combined_arms_v5,
     "magent/gather_v4": gather_v4,
     "magent/tiger_deer_v3": tiger_deer_v3,

test/all_parameter_combs.py

@@ -42,32 +42,32 @@
     (texas_holdem_no_limit_v6, dict(num_players=3)),
     (texas_holdem_no_limit_v6, dict(num_players=4)),
 
-    (knights_archers_zombies_v8, dict(spawn_rate=50)),
-    (knights_archers_zombies_v8, dict(num_knights=4, num_archers=5)),
-    (knights_archers_zombies_v8, dict(killable_knights=True, killable_archers=True)),
-    (knights_archers_zombies_v8, dict(killable_knights=False, killable_archers=False)),
-    (knights_archers_zombies_v8, dict(line_death=False)),
-    (knights_archers_zombies_v8, dict(pad_observation=False)),
-    (knights_archers_zombies_v8, dict(max_cycles=100)),
+    (knights_archers_zombies_v9, dict(spawn_rate=50)),
+    (knights_archers_zombies_v9, dict(num_knights=4, num_archers=5)),
+    (knights_archers_zombies_v9, dict(killable_knights=True, killable_archers=True)),
+    (knights_archers_zombies_v9, dict(killable_knights=False, killable_archers=False)),
+    (knights_archers_zombies_v9, dict(line_death=False)),
+    (knights_archers_zombies_v9, dict(pad_observation=False)),
+    (knights_archers_zombies_v9, dict(max_cycles=100)),
 
     (pistonball_v6, dict(continuous=True)),
     (pistonball_v6, dict(n_pistons=30)),
     (pistonball_v6, dict(continuous=False)),
     (pistonball_v6, dict(random_drop=True, random_rotate=True)),
     (pistonball_v6, dict(random_drop=False, random_rotate=False)),
 
-    (prison_v3, dict(continuous=True)),
-    (prison_v3, dict(continuous=False)),
-    (prison_v3, dict(vector_observation=True)),
-    (prison_v3, dict(vector_observation=False)),
-    (prison_v3, dict(num_floors=1)),
-    (prison_v3, dict(num_floors=5)),
-    (prison_v3, dict(synchronized_start=True)),
-    (prison_v3, dict(synchronized_start=False)),
-    (prison_v3, dict(identical_aliens=True)),
-    (prison_v3, dict(identical_aliens=False)),
-    (prison_v3, dict(random_aliens=True)),
-    (prison_v3, dict(random_aliens=False)),
+    (prison_v4, dict(continuous=True)),
+    (prison_v4, dict(continuous=False)),
+    (prison_v4, dict(vector_observation=True)),
+    (prison_v4, dict(vector_observation=False)),
+    (prison_v4, dict(num_floors=1)),
+    (prison_v4, dict(num_floors=5)),
+    (prison_v4, dict(synchronized_start=True)),
+    (prison_v4, dict(synchronized_start=False)),
+    (prison_v4, dict(identical_aliens=True)),
+    (prison_v4, dict(identical_aliens=False)),
+    (prison_v4, dict(random_aliens=True)),
+    (prison_v4, dict(random_aliens=False)),
 
     (prospector_v4, dict(ind_reward=0.8, group_reward=0.1, other_group_reward=0.1,
                          prospec_find_gold_reward=1, prospec_handoff_gold_reward=1, banker_receive_gold_reward=1,
@@ -90,13 +90,13 @@
 
     (tiger_deer_v3, dict(minimap_mode=True)),
     (battle_v3, dict(minimap_mode=False)),
-    (battlefield_v3, dict(minimap_mode=False, extra_features=False)),
-    (battlefield_v3, dict(minimap_mode=False, extra_features=True)),
-    (battlefield_v3, dict(minimap_mode=True, extra_features=False)),
-    (battlefield_v3, dict(minimap_mode=True, extra_features=True)),
+    (battlefield_v4, dict(minimap_mode=False, extra_features=False)),
+    (battlefield_v4, dict(minimap_mode=False, extra_features=True)),
+    (battlefield_v4, dict(minimap_mode=True, extra_features=False)),
+    (battlefield_v4, dict(minimap_mode=True, extra_features=True)),
     (adversarial_pursuit_v3, dict(map_size=15)),
     (battle_v3, dict(map_size=15)),
-    (battlefield_v3, dict(map_size=46)),
+    (battlefield_v4, dict(map_size=46)),
     (combined_arms_v5, dict(map_size=16)),
     (tiger_deer_v3, dict(map_size=15)),