def run():
"""Run the agent for a finite number of trials."""
options = parseOptions()
env = Environment() # create environment (also adds some dummy traffic)
sim = Simulator(
env, update_delay=0, display=options.display
) # create simulator (uses pygame when display=True, if available)
results = {}
from settings import params
for agent, symbol in [(options.player1, 1), (options.player2, -1)]:
kwargs = params[agent]
env.add_agent(symbol=symbol,
file=options.file,
clear=options.clear,
save=options.save,
**kwargs)
sim.run(
n_trials=options.iterations) # run for a specified number of trials
for agent in env.agents:
results["X" if agent.symbol == 1 else 'O'] = agent.wins
print results
dispatcher.send(signal='main.complete', sender={})
def run():
"""Run the agent for a finite number of trials."""
options = parseOptions()
env = Environment() # create environment (also adds some dummy traffic)
sim = Simulator(env, update_delay=0, display=options.display) # create simulator (uses pygame when display=True, if available)
results = {}
from settings import params
for agent, symbol in [(options.player1, 1), (options.player2, -1)]:
kwargs = params[agent]
env.add_agent(
symbol=symbol,
file=options.file,
clear=options.clear,
save=options.save,
**kwargs)
sim.run(n_trials=options.iterations) # run for a specified number of trials
for agent in env.agents:
results["X" if agent.symbol == 1 else 'O'] = agent.wins
print results
dispatcher.send(signal='main.complete', sender={})
def main():
env = Environment(10, 10, magnification=80)
robot = Agent(env)
env.add_agent(robot)
env.starting_agent_location()
for i in range(50):
# make the robot sense the env and update beiliefs
robot.sense(env.get_obs())
env.draw()
env.step(robot.do_move())
# print(env.agent_state)
# print(robot)
# print(robot.p.sum())
return None
self.environment = environment
def run(self):
while(True):
# Movement of targets eq.(2):
if(np.random.random() > 0.9999):
print("Change speed!")
with self.lock:
self.environment.set_targets_command((np.random.random((self.environment.xi.shape))-0.5))
self.environment.update()
time.sleep(self.environment.t)
env = Environment(10,10,0.01, True)
for i in range(5):
env.add_target(np.random.random()*2.5-2.5, np.random.random()*2.5-2.5, 0.005, 0.005)
env.add_agent(np.random.random()*2.5-2.5, np.random.random()*2.5-2.5, 0.005, 0.005)
# env.add_agent(np.random.random()*2.5-2.5, np.random.random()*2.5-2.5, 0.005, 0.005)
main = Main(env)
main.start()
#main.run()
plt.gcf()
plt.show()
# plt.savefig("output/" + "MRS" + str(time.time()) + ".png")
main.join()
# To recover a final video of de execution:
# ffmpeg -f image2 -s 1920x1080 -i output/MRS%5d.png -vcodec libx264 -crf 25 -pix_fmt yuv420p MRS.mp4
