def __init__(self, env=None, maxsteps=1000, desiredValue=0):
"""
:key env: (optional) an instance of a CartPoleEnvironment (or a subclass thereof)
:key maxsteps: maximal number of steps (default: 1000)
"""
self.desiredValue = desiredValue
if env == None:
env = CartPoleEnvironment()
EpisodicTask.__init__(self, env)
self.N = maxsteps
self.t = 0
# scale position and angle, don't scale velocities (unknown maximum)
self.sensor_limits = [(-3, 3)]
for i in range(1, self.outdim):
if isinstance(self.env, NonMarkovPoleEnvironment) and i % 2 == 0:
self.sensor_limits.append(None)
else:
self.sensor_limits.append((-pi, pi))
# self.sensor_limits = [None] * 4
# actor between -10 and 10 Newton
self.actor_limits = [(-50, 50)]
def __init__(self):
self.p1 = CartPoleEnvironment()
self.p2 = CartPoleEnvironment()
self.p2.l = 0.05
self.p2.mp = 0.01
self.reset()
