def main():
# Init loggers
log.set_level("fine")
log.set_sync(False)
agent_log.set_level("fine")
agent_log.set_sync(False)
ure_logger().set_level("fine")
ure_logger().set_sync(False)
# Set main atomspace
atomspace = AtomSpace()
set_default_atomspace(atomspace)
# Wrap environment
wrapped_env = CartPoleWrapper(env, atomspace)
# Instantiate CartPoleAgent, and tune parameters
cpa = FixedCartPoleAgent(wrapped_env, atomspace)
cpa.delta = 1.0e-16
# Run control loop
while not cpa.control_cycle():
wrapped_env.render()
time.sleep(0.1)
log.info("cycle_count = {}".format(cpa.cycle_count))
log_msg(agent_log, f"The final reward is {cpa.accumulated_reward}.")
def __init__(self,
env: CartPoleWrapper,
atomspace: AtomSpace,
log_level="debug"):
set_default_atomspace(atomspace)
# Create Action Space. The set of allowed actions an agent can take.
# TODO take care of action parameters.
action_space = {ExecutionLink(SchemaNode(a)) for a in env.action_names}
# Create Goal
pgoal = EvaluationLink(PredicateNode("Reward"), NumberNode("1"))
ngoal = EvaluationLink(PredicateNode("Reward"), NumberNode("0"))
# Call super ctor
super().__init__(env,
atomspace,
action_space,
pgoal,
ngoal,
log_level=log_level)
# Overwrite some OpencogAgent parameters
self.monoaction_general_succeedent_mining = False
self.polyaction_mining = False
self.temporal_deduction = False
def __init__(self,
env: Env,
atomspace: AtomSpace,
action_names: list[str] = []):
super().__init__()
self.atomspace = atomspace
set_default_atomspace(self.atomspace)
self.env = env
self.action_space = env.action_space
self.observation_space = env.observation_space
self.action_names = action_names
def __init__(self, env: CartPoleWrapper, atomspace: AtomSpace):
set_default_atomspace(atomspace)
# Create Action Space. The set of allowed actions an agent can take.
# TODO take care of action parameters.
action_space = {ExecutionLink(SchemaNode(a)) for a in env.action_names}
# Create Goal
pgoal = EvaluationLink(PredicateNode("Reward"), NumberNode("1"))
ngoal = EvaluationLink(PredicateNode("Reward"), NumberNode("0"))
# Call super ctor
super().__init__(env, atomspace, action_space, pgoal, ngoal)
def test_cartpole():
env = gym.make("CartPole-v1")
# Set main atomspace
atomspace = AtomSpace()
set_default_atomspace(atomspace)
# Wrap environment
wrapped_env = CartPoleWrapper(env, atomspace)
# Instantiate CartPoleAgent, and tune parameters
cpa = FixedCartPoleAgent(wrapped_env, atomspace)
cpa.delta = 1.0e-16
# Run control loop
while not cpa.control_cycle():
time.sleep(0.1)
def __init__(self, env, atomspace):
set_default_atomspace(atomspace)
# Create Action Space. The set of allowed actions an agent can take.
# TODO take care of action parameters.
action_space = {ExecutionLink(SchemaNode(a)) for a in env.action_names}
# Create Goal
pgoal = EvaluationLink(PredicateNode("Reward"), NumberNode("1"))
ngoal = EvaluationLink(PredicateNode("Reward"), NumberNode("0"))
# Call super ctor
OpencogAgent.__init__(self, env, atomspace, action_space, pgoal, ngoal)
# Overwrite some OpencogAgent parameters
self.polyaction_mining = False
self.monoaction_general_succeedent_mining = True
self.temporal_deduction = True
self.cogscm_minimum_strength = 0.9
self.cogscm_maximum_shannon_entropy = 1
self.cogscm_maximum_differential_entropy = 0
self.cogscm_maximum_variables = 0
def eat(self, i):
self.env.step(mk_action("move", 0))
self.env.step(mk_action("hotbar.{}".format(i), 1))
self.env.step(mk_action("hotbar.{}".format(i), 0))
self.env.step(mk_action("use", 1))
def wake(self):
self.env.step(mk_action("use", 0))
self.env.step(mk_action("hotbar.9", 1))
self.env.step(mk_action("hotbar.9", 0))
if __name__ == "__main__":
atomspace = AtomSpace()
set_default_atomspace(atomspace)
# Wrap environment
wrapped_env = MalmoWrapper(missionXML=mission_xml, validate=True)
# Create Goal
pgoal = EvaluationLink(PredicateNode("Reward"), NumberNode("1"))
ngoal = EvaluationLink(PredicateNode("Reward"), NumberNode("0"))
# Create Action Space. The set of allowed actions an agent can take.
# TODO take care of action parameters.
action_space = {
ExecutionLink(SchemaNode("tpz"), NumberNode("2.5")),
ExecutionLink(SchemaNode("tpz"), NumberNode("-1.5")),
ExecutionLink(SchemaNode("attack"), NumberNode("0")),
ExecutionLink(SchemaNode("attack"), NumberNode("1")),
ExecutionLink(SchemaNode("move"), NumberNode("0")),
