def handle_gym_message(self, envelope: Envelope) -> None:
"""
Forward a message to gym.
:param envelope: the envelope
:return: None
"""
gym_message = GymSerializer().decode(envelope.message)
gym_message = cast(GymMessage, gym_message)
if gym_message.performative == GymMessage.Performative.ACT:
action = gym_message.action.any
step_id = gym_message.step_id
observation, reward, done, info = self.gym_env.step(action) # type: ignore
msg = GymMessage(
performative=GymMessage.Performative.PERCEPT,
observation=GymMessage.AnyObject(observation),
reward=reward,
done=done,
info=GymMessage.AnyObject(info),
step_id=step_id,
)
msg_bytes = GymSerializer().encode(msg)
envelope = Envelope(
to=envelope.sender,
sender=DEFAULT_GYM,
protocol_id=GymMessage.protocol_id,
message=msg_bytes,
)
self._send(envelope)
elif gym_message.performative == GymMessage.Performative.RESET:
self.gym_env.reset() # type: ignore
elif gym_message.performative == GymMessage.Performative.CLOSE:
self.gym_env.close() # type: ignore
def _decode_percept(self, envelope: Envelope,
expected_step_id: int) -> Message:
"""
Receive the response from the gym environment in the form of an envelope and decode it.
The response is a PERCEPT message containing the usual 'observation', 'reward', 'done', 'info' parameters.
:param expected_step_id: the expected step id
:return: a message received as a response to the action performed in apply_action.
"""
if envelope is not None:
if envelope.protocol_id == PublicId.from_str("fetchai/gym:0.1.0"):
gym_msg = GymSerializer().decode(envelope.message)
gym_msg_performative = GymMessage.Performative(
gym_msg.get("performative"))
gym_msg_step_id = gym_msg.get("step_id")
if (gym_msg_performative == GymMessage.Performative.PERCEPT
and gym_msg_step_id == expected_step_id):
return gym_msg
else:
raise ValueError(
"Unexpected performative or no step_id: {}".format(
gym_msg_performative))
else:
raise ValueError("Unknown protocol_id: {}".format(
envelope.protocol_id))
else:
raise ValueError("Missing envelope.")
def test_gym_serialization():
"""Test that the serialization for the 'simple' protocol works for the ERROR message."""
msg = GymMessage(
performative=GymMessage.Performative.ACT, action="any_action", step_id=1
)
msg_bytes = GymSerializer().encode(msg)
actual_msg = GymSerializer().decode(msg_bytes)
expected_msg = msg
assert expected_msg == actual_msg
msg = GymMessage(
performative=GymMessage.Performative.PERCEPT,
observation="any_observation",
reward=0.0,
info={"some_key": "some_value"},
done=True,
step_id=1,
)
msg_bytes = GymSerializer().encode(msg)
actual_msg = GymSerializer().decode(msg_bytes)
expected_msg = msg
assert expected_msg == actual_msg
def close(self) -> None:
"""
Close the environment.
:return: None
"""
self._is_rl_agent_trained = True
gym_msg = GymMessage(performative=GymMessage.Performative.CLOSE)
gym_bytes = GymSerializer().encode(gym_msg)
envelope = Envelope(
to=DEFAULT_GYM,
sender=self._skill_context.agent_address,
protocol_id=GymMessage.protocol_id,
message=gym_bytes,
)
self._skill_context.outbox.put(envelope)
async def test_send_connection_error(self):
"""Test send connection error."""
msg = GymMessage(performative=GymMessage.Performative.ACT,
action="any_action",
step_id=1)
msg_bytes = GymSerializer().encode(msg)
envelope = Envelope(
to="_to_key",
sender="_from_key",
protocol_id=GymMessage.protocol_id,
message=msg_bytes,
)
self.gym_con.connection_status.is_connected = False
with pytest.raises(ConnectionError):
await self.gym_con.send(envelope)
def reset(self) -> None:
"""
Reset the environment.
:return: None
"""
self._step_count = 0
self._is_rl_agent_trained = False
gym_msg = GymMessage(performative=GymMessage.Performative.RESET)
gym_bytes = GymSerializer().encode(gym_msg)
envelope = Envelope(
to=DEFAULT_GYM,
sender=self._skill_context.agent_address,
protocol_id=GymMessage.protocol_id,
message=gym_bytes,
)
self._skill_context.outbox.put(envelope)
def reset(self) -> None:
"""
Reset the environment.
:return: None
"""
if not self._agent.multiplexer.is_connected:
self._connect()
gym_msg = GymMessage(performative=GymMessage.Performative.RESET)
gym_bytes = GymSerializer().encode(gym_msg)
envelope = Envelope(
to=DEFAULT_GYM,
sender=self._agent_address,
protocol_id=GymMessage.protocol_id,
message=gym_bytes,
)
self._agent.outbox.put(envelope)
def _encode_action(self, action: Action, step_id: int) -> Envelope:
"""
Encode the 'action' sent to the step function as one or several envelopes.
:param action: the action that is the output of an RL algorithm.
:param step_id: the step id
:return: an envelope
"""
gym_msg = GymMessage(performative=GymMessage.Performative.ACT,
action=action,
step_id=step_id)
gym_bytes = GymSerializer().encode(gym_msg)
envelope = Envelope(
to=DEFAULT_GYM,
sender=self._skill_context.agent_address,
protocol_id=GymMessage.protocol_id,
message=gym_bytes,
)
return envelope