define simple action and observation space

jgocm · Aug 12, 2020 · 97bf70f · 97bf70f
1 parent a99b190
commit 97bf70f
Show file tree

Hide file tree

Showing 12 changed files with 71 additions and 7 deletions.
diff --git a/.gitignore b/.gitignore
@@ -1,3 +1,4 @@
 .DS_Store
-grsim_ssl/__pycache__/*
+*.pyc
+gym_ssl.egg-info/
 pb/*
diff --git a/gym_ssl/grsim_ssl/grSimClient.py b/gym_ssl/grsim_ssl/grSimClient.py
@@ -1,6 +1,6 @@
 import socket
-import pb.messages_robocup_ssl_wrapper_pb2 as wrapper_pb2
-import pb.grSim_Packet_pb2 as packet_pb2
+import gym_ssl.grsim_ssl.pb.messages_robocup_ssl_wrapper_pb2 as wrapper_pb2
+import gym_ssl.grsim_ssl.pb.grSim_Packet_pb2 as packet_pb2
 
 
 class grSimClient:

diff --git a/gym_ssl/grsim_ssl/grSimSSL_env.py b/gym_ssl/grsim_ssl/grSimSSL_env.py
@@ -1,11 +1,66 @@
 import gym
+import math
+import numpy as np
+
+from gym_ssl.grsim_ssl.grSimClient import grSimClient
 
 
 class GrSimSSLEnv(gym.Env):
+    """
+    Using cartpole env description as base example for our documentation
+    Description:
+        A pole is attached by an un-actuated joint to a cart, which moves along
+        a frictionless track. The pendulum starts upright, and the goal is to
+        prevent it from falling over by increasing and reducing the cart's
+        velocity.
+    Source:
+        This environment corresponds to the version of the cart-pole problem
+        described by Barto, Sutton, and Anderson
+    Observation:
+        Type: Box(3)
+        Num     Observation                  Min                     Max
+        0       id 0 Blue Team Robot X       -Inf                    Inf
+        1       id 0 Blue Team Robot Y       -Inf                    Inf
+        2       id 0 Blue Team Robot Angle   -3.1416                 3.1416
+
+    Actions:
+        Type: Box(3)
+        Num     Action                        Min                     Max
+        0       id 0 Blue Team Robot Vx       -1                      1
+        1       id 0 Blue Team Robot Vy       -1                      1
+        2       id 0 Blue Team Robot Omega    -1                      1
+        Note: The amount the velocity that is reduced or increased is not
+        fixed; it depends on the angle the pole is pointing. This is because
+        the center of gravity of the pole increases the amount of energy needed
+        to move the cart underneath it
+    Reward:
+        Reward is 1 for every step taken, including the termination step
+    Starting State:
+        All observations are assigned a uniform random value in [-0.05..0.05]
+    Episode Termination: 
+        Pole Angle is more than 12 degrees.
+        Cart Position is more than 2.4 (center of the cart reaches the edge of
+        the display).
+        Episode length is greater than 200.
+        Solved Requirements:
+        Considered solved when the average return is greater than or equal to
+        195.0 over 100 consecutive trials.
+    """
 
     def __init__(self):
+        self.client = grSimClient()
+
+        self.action_space = gym.spaces.Box(low=-1, high=1, shape=(3,), dtype=np.float32)
+        # Observation Space thresholds
+        obsSpaceThresholds = np.array([np.finfo(np.float32).max,
+                                       np.finfo(np.float32).max,
+                                       math.pi], dtype=np.float32)
+        self.observation_space = gym.spaces.Box(low=-obsSpaceThresholds, high=obsSpaceThresholds)
+
         print('Environment initialized')
+
     def step(self):
         print('step sucessful!')
+        return self.observation_space.sample()
     def reset(self):
         print('Environment reset')
diff --git a/gym_ssl/grsim_ssl/pb/__pycache__/grSim_Commands_pb2.cpython-38.pyc b/gym_ssl/grsim_ssl/pb/__pycache__/grSim_Commands_pb2.cpython-38.pyc
diff --git a/gym_ssl/grsim_ssl/pb/__pycache__/grSim_Packet_pb2.cpython-38.pyc b/gym_ssl/grsim_ssl/pb/__pycache__/grSim_Packet_pb2.cpython-38.pyc
diff --git a/gym_ssl/grsim_ssl/pb/__pycache__/grSim_Replacement_pb2.cpython-38.pyc b/gym_ssl/grsim_ssl/pb/__pycache__/grSim_Replacement_pb2.cpython-38.pyc
diff --git a/gym_ssl/grsim_ssl/pb/__pycache__/messages_robocup_ssl_detection_pb2.cpython-38.pyc b/gym_ssl/grsim_ssl/pb/__pycache__/messages_robocup_ssl_detection_pb2.cpython-38.pyc
diff --git a/gym_ssl/grsim_ssl/pb/__pycache__/messages_robocup_ssl_geometry_pb2.cpython-38.pyc b/gym_ssl/grsim_ssl/pb/__pycache__/messages_robocup_ssl_geometry_pb2.cpython-38.pyc
diff --git a/gym_ssl/grsim_ssl/pb/__pycache__/messages_robocup_ssl_wrapper_pb2.cpython-38.pyc b/gym_ssl/grsim_ssl/pb/__pycache__/messages_robocup_ssl_wrapper_pb2.cpython-38.pyc
diff --git a/gym_ssl/grsim_ssl/pb/grSim_Packet_pb2.py b/gym_ssl/grsim_ssl/pb/grSim_Packet_pb2.py
diff --git a/gym_ssl/grsim_ssl/pb/messages_robocup_ssl_wrapper_pb2.py b/gym_ssl/grsim_ssl/pb/messages_robocup_ssl_wrapper_pb2.py
diff --git a/test.py b/test.py
@@ -0,0 +1,8 @@
+import gym
+import gym_ssl
+
+env = gym.make('grSimSSL-v0')
+env.step()
+env.reset()
+print(env.action_space.sample())
+print(env.observation_space.sample())