columbus/env.py

@@ -166,7 +166,6 @@ class ColumbusEnv(gym.Env):
 
     def reset(self):
         pygame.init()
-        self._seed(self.env_seed)
         self._rendered = False
         self.inp = (0.5, 0.5)
         self.keypress_timeout = 0
@@ -179,6 +178,7 @@ class ColumbusEnv(gym.Env):
         self.agent = entities.Agent(self)
         self.setup()
         self.entities.append(self.agent)  # add it last, will be drawn on top
+        self._seed(self.env_seed)
         self.observable._entities = None
         return self.observable.get_observation()
 
@@ -206,8 +206,6 @@ class ColumbusEnv(gym.Env):
             self.keypress_timeout = int(self.fps/2)
             if keys[pygame.K_m]:
                 self.draw_entities = not self.draw_entities
-            elif keys[pygame.K_r]:
-                self.reset()
             else:
                 self.keypress_timeout = 0
         else:
@@ -363,7 +361,7 @@ class ColumbusJustState(ColumbusEnv):
 
 
 class ColumbusStateWithBarriers(ColumbusEnv):
-    def __init__(self, observable=observables.StateObservable(coordsAgent=True, speedAgent=False, coordsRelativeToAgent=False, coordsRewards=True, rewardsWhitelist=None, coordsEnemys=True, enemysWhitelist=None, enemysNoBarriers=True, rewardsTimeouts=False, include_rand=True), fps=30, env_seed=3.141):
+    def __init__(self, observable=observables.StateObservable(coordsAgent=True, speedAgent=False, coordsRelativeToAgent=False, coordsRewards=True, rewardsWhitelist=None, coordsEnemys=True, enemysWhitelist=None, enemysNoBarriers=True, rewardsTimeouts=False, include_rand=True), fps=30, env_seed=3.1):
         super(ColumbusStateWithBarriers, self).__init__(
             observable=observable,  fps=fps, env_seed=env_seed)
         self.aux_reward_max = 0.01
@@ -375,9 +373,9 @@ class ColumbusStateWithBarriers(ColumbusEnv):
             enemy = entities.CircleBarrier(self)
             enemy.radius = self.random()*25+75
             self.entities.append(enemy)
-        for i in range(1):
+        for i in range(3):
             enemy = entities.FlyingChaser(self)
-            enemy.chase_acc = 0.55  # *0.6+0.5
+            enemy.chase_acc = self.random()*0.4+0.3  # *0.6+0.5
             self.entities.append(enemy)
         for i in range(1):
             reward = entities.TeleportingReward(self)

columbus/humanPlayer.py

@@ -1,5 +1,5 @@
 from time import sleep, time
-import env
+from env import *
 import numpy as np
 import pygame
 
@@ -7,37 +7,13 @@ from observables import Observable, CnnObservable
 
 
 def main():
-    Env = chooseEnv()
-    env = Env(fps=30)
+    #env = ColumbusTest3_1(fps=30)
+    env = ColumbusStateWithBarriers(fps=30)
     env.start_pos = [0.6, 0.3]
     playEnv(env)
     env.close()
 
 
-def getAvaibleEnvs():
-    # kinda hacky... idk
-    strs = dir(env)
-    for s in strs:
-        if s.startswith('Columbus') and s != 'ColumbusEnv':
-            yield getattr(env, s)
-
-
-def chooseEnv():
-    envs = list(getAvaibleEnvs())
-    for i, Env in enumerate(envs):
-        print('['+str(i)+'] '+Env.__name__)
-    while True:
-        inp = input('[#> ')
-        try:
-            i = int(inp)
-        except:
-            print('[!] You have to enter the number...')
-        if i < 0 or i >= len(envs):
-            print(
-                '[!] That is a number, but not one that makes sense in this context...')
-        return envs[i]
-
-
 def playEnv(env):
     env.reset()
     done = False

columbus/observables.py

@@ -58,10 +58,10 @@ class CnnObservable(Observable):
         snap = self.env.surface.subsurface(rect)
         self.snap = pygame.Surface((self.in_width, self.in_height))
         if self.env.void_barrier:
-            col = (255, 0, 0)
+            col = (223, 0, 0)
         else:
             col = (50, 50, 50)
-        pygame.draw.rect(self.snap, col,
+        pygame.draw.rect(self.snap, (50, 50, 50),
                          pygame.Rect(0, 0, self.in_width, self.in_height))
         self.snap.blit(snap, (cx - x, cy - y))
         self.obs = self.scaler(