Merge branch 'randomization' into add_preprocess_action - bring in fixes, avoid rebase

bin/HFO

@@ -2,7 +2,13 @@
 # encoding: utf-8
 from __future__ import print_function
 
-import subprocess, os, time, numpy, sys
+import atexit
+import numpy
+import os
+import time
+import signal
+import subprocess
+import sys
 
 # Global list of all/essential running processes
 processes, necProcesses = [], []
@@ -12,6 +18,16 @@ SERVER_BIN = 'rcssserver'
 # Command to run the monitor. Edit as needed; ditto to the above re directories.
 MONITOR_BIN = 'soccerwindow2'
 
+def cleanup():
+  """Cleanup even if doing SystemExit, as with term."""
+  for p in reversed(processes):
+    p.terminate()
+    time.sleep(0.1)
+    p.kill()
+
+def term(received_signal, ignored_stack):
+  sys.exit("Signal {0!r} received; exiting".format(received_signal))
+
 def launch(cmd, name = 'Unknown', necessary = True, suppressOutput = True):
   """Launch a process.
 
@@ -22,8 +38,8 @@ def launch(cmd, name = 'Unknown', necessary = True, suppressOutput = True):
   """
   kwargs = {}
   if suppressOutput:
-    kwargs = {'stdout': open('/dev/null', 'w'),
-              'stderr': open('/dev/null', 'w')}
+    kwargs = {'stdout': open(os.devnull, 'w'),
+              'stderr': open(os.devnull, 'w')}
   try:
     p = subprocess.Popen(cmd.split(' '), shell = False, **kwargs)
   except (IOError, OSError):
@@ -69,6 +85,13 @@ def main(args):
                     args.min_ball_x, args.max_ball_x, args.messageSize,
                     args.verbose)
 
+  try:
+    signal.signal(signal.SIGTERM, term)
+  except (ValueError, AttributeError):
+    print("Not able to catch sigterm")
+
+  atexit.register(cleanup)
+
   try:
     # Launch the Server
     server = launch(serverCommand + serverOptions, name='server',

example/defense_python_2v3.sh

+#!/bin/bash
+
+./bin/HFO --offense-npcs=2 --defense-agents=1 --defense-npcs=2 --trials 20 --headless &
+sleep 5
+./example/hand_coded_defense_agent.py &> agent1.txt &
+sleep 5
+
+# The magic line
+#   $$ holds the PID for this script
+#   Negation means kill by process group id instead of PID
+trap "kill -TERM -$$" SIGINT
+wait
\ No newline at end of file

example/hand_coded_defense_agent.py

@@ -221,12 +221,22 @@ def main():
       print("Python randomization seed useless without --epsilon >0")
   if args.epsilon > 0:
     print("Using epsilon {0:n}".format(args.epsilon))
+  my_unum = hfo_env.getUnum()
+  assert ((my_unum > 1) and (my_unum <= 11)), "Bad unum {!r}".format(my_unum)
+  print("My unum is {0:d}".format(my_unum))
   for episode in itertools.count():
-    old_ball_pos_x = 0
+    old_ball_pos_x = -1
     old_ball_pos_y = 0
+    episode_start = True
     status = hfo.IN_GAME
     while status == hfo.IN_GAME:
       state = hfo_env.getState()
+      if episode_start:
+        if (state[3] >= -1) and (state[3] <= 1):
+          old_ball_pos_x = state[3]
+        if (state[4] >= -1) and (state[4] <= 1):
+          old_ball_pos_y = state[4]
+        episode_start = False
       if (args.epsilon > 0) and (random.random() < args.epsilon):
         do_random_defense_action(state, hfo_env)
       else: