init commit

.gitignore

@@ -0,0 +1 @@
+.DS_STORE

gym_risk/__init__.py

@@ -0,0 +1,6 @@
+from gym.envs.registration import register
+
+register(
+    id='risk-v0',
+    entry_point='gym_risk.envs:RiskEnv',
+)

gym_risk/envs/__init__.py

@@ -0,0 +1 @@
+from gym_risk.envs.risk_env import RiskEnv 

gym_risk/envs/risk_env.py

@@ -0,0 +1,60 @@
+import gym
+
+class RiskEnv(gym.Env):
+    metadata = {'render.modes': ['human']}
+
+    def __init__(self):
+        pass
+
+    def _step(self, action):
+        """
+        Parameters
+        ----------
+        action :
+
+        Returns
+        -------
+        ob, reward, episode_over, info : tuple
+            ob (object) :
+                an environment-specific object representing your observation of
+                the environment.
+            reward (float) :
+                amount of reward achieved by the previous action. The scale
+                varies between environments, but the goal is always to increase
+                your total reward.
+            episode_over (bool) :
+                whether it's time to reset the environment again. Most (but not
+                all) tasks are divided up into well-defined episodes, and done
+                being True indicates the episode has terminated. (For example,
+                perhaps the pole tipped too far, or you lost your last life.)
+            info (dict) :
+                 diagnostic information useful for debugging. It can sometimes
+                 be useful for learning (for example, it might contain the raw
+                 probabilities behind the environment's last state change).
+                 However, official evaluations of your agent are not allowed to
+                 use this for learning.
+        """
+        self._take_action(action)
+        self.status = self.env.step()
+        reward = self._get_reward()
+        ob = self.env.getState()
+        episode_over = self.status != hfo_py.IN_GAME
+        return ob, reward, episode_over, {}
+
+    def _reset(self):
+        pass
+
+    def _render(self, mode='human', close=False):
+        pass
+
+    def _take_action(self, action):
+        pass
+
+    def _get_reward(self):
+        """ Reward is given for XY. """
+        if self.status == FOOBAR:
+            return 1
+        elif self.status == ABC:
+            return self.somestate ** 2
+        else:
+            return 0

gym_risk/map.py

@@ -0,0 +1,24 @@
+import random
+import networkx as nx
+
+from maps.debug import debug
+
+class Map():
+    metadata = {}
+
+    def __init__(self):
+        self.graph = None
+        pass
+
+    def initialize_player_assignment(self):
+        """Randomly assigns each player a country until there are none left"""
+
+
+        pass
+
+    def change_ownership(self, payload):
+        """Change ownership of a country
+        Params: payload (dict) {node:player}
+        """
+        nx.set_node_attributes(self.graph, payload, "owner")
+        pass

gym_risk/maps/debug.py

@@ -0,0 +1,17 @@
+import networkx as nx
+
+debug = nx.Graph()
+
+debug.add_node("Thousand Oaks", continent="California", color="red")
+debug.add_node("San Francisco", continent="California", color="red")
+debug.add_node("Sacramento", continent="California", color="red")
+debug.add_node("Provo", continent="Utah", color="blue")
+debug.add_node("South Jordan", continent="Utah", color="blue")
+
+debug.add_edge("South Jordan", "Provo")
+debug.add_edge("South Jordan", "San Francisco")
+debug.add_edge("Thousand Oaks", "San Francisco")
+debug.add_edge("Provo", "San Francisco")
+debug.add_edge("San Francisco", "Sacramento")
+debug.add_edge("Sacramento", "Thousand Oaks")
+debug.add_edge("Sacramento", "Provo")

gym_risk/viz.py

@@ -0,0 +1,4 @@
+### File for visualizing the map
+from matplotlib import pyplot as plt
+import networkx as nx
+

setup.py

@@ -0,0 +1,10 @@
+from setuptools import setup
+
+setup(name='gym_risk',
+      version='0.0.1',
+      install_requires=['gym', 
+            'networkx',
+            'geopandas',
+            'descartes',
+            ]  # And any other dependencies risk needs
+)