Initial commit

packages/openpi-client/src/openpi_client/runtime/agent.py

@@ -0,0 +1,13 @@
+import abc
+
+
+class Agent(abc.ABC):
+    """An Agent is the thing with agency, i.e. the entity that makes decisions.
+
+    Agents receive observations about the state of the world, and return actions
+    to take in response.
+    """
+
+    @abc.abstractmethod
+    def get_action(self, observation: dict) -> dict:
+        """Query the agent for the next action."""

packages/openpi-client/src/openpi_client/runtime/agents/policy_agent.py

@@ -0,0 +1,15 @@
+from openpi_client import base_policy as _base_policy
+from openpi_client.runtime import agent as _agent
+from typing_extensions import override
+
+
+# TODO: Consider unifying policies and agents.
+class PolicyAgent(_agent.Agent):
+    """An agent that uses a policy to determine actions."""
+
+    def __init__(self, policy: _base_policy.BasePolicy) -> None:
+        self._policy = policy
+
+    @override
+    def get_action(self, observation: dict) -> dict:
+        return self._policy.infer(observation)

packages/openpi-client/src/openpi_client/runtime/environment.py

@@ -0,0 +1,32 @@
+import abc
+
+
+class Environment(abc.ABC):
+    """An Environment represents the robot and the environment it inhabits.
+
+    The primary contract of environments is that they can be queried for observations
+    about their state, and have actions applied to them to change that state.
+    """
+
+    @abc.abstractmethod
+    def reset(self) -> None:
+        """Reset the environment to its initial state.
+
+        This will be called once before starting each episode.
+        """
+
+    @abc.abstractmethod
+    def done(self) -> bool:
+        """Allow the environment to signal that the task is done.
+
+        This will be called after each step. It should return `True` if the task is
+        done (either successfully or unsuccessfully), and `False` otherwise.
+        """
+
+    @abc.abstractmethod
+    def get_observation(self) -> dict:
+        """Query the environment for the current state."""
+
+    @abc.abstractmethod
+    def apply_action(self, action: dict) -> None:
+        """Take an action in the environment."""

packages/openpi-client/src/openpi_client/runtime/runtime.py

@@ -0,0 +1,78 @@
+import logging
+import threading
+import time
+
+from openpi_client.runtime import agent as _agent
+from openpi_client.runtime import environment as _environment
+from openpi_client.runtime import subscriber as _subscriber
+
+
+class Runtime:
+    """The core module orchestrating interactions between key components of the system."""
+
+    def __init__(
+        self,
+        environment: _environment.Environment,
+        agent: _agent.Agent,
+        subscribers: list[_subscriber.Subscriber],
+        max_hz: float = 0,
+    ) -> None:
+        self._environment = environment
+        self._agent = agent
+        self._subscribers = subscribers
+        self._max_hz = max_hz
+
+        self._running = False
+
+    def run(self) -> None:
+        """Runs the runtime loop continuously until stop() is called or the environment is done."""
+        self._loop()
+
+    def run_in_new_thread(self) -> threading.Thread:
+        """Runs the runtime loop in a new thread."""
+        thread = threading.Thread(target=self.run)
+        thread.start()
+        return thread
+
+    def stop(self) -> None:
+        """Stops the runtime loop."""
+        self._running = False
+
+    def _loop(self) -> None:
+        """The runtime loop."""
+        logging.info("Starting episode...")
+        self._environment.reset()
+        for subscriber in self._subscribers:
+            subscriber.on_episode_start()
+
+        self._running = True
+        step_time = 1 / self._max_hz if self._max_hz > 0 else 0
+        last_step_time = time.time()
+
+        while self._running:
+            self._step()
+
+            # Sleep to maintain the desired frame rate
+            now = time.time()
+            dt = now - last_step_time
+            if dt < step_time:
+                time.sleep(step_time - dt)
+                last_step_time = time.time()
+            else:
+                last_step_time = now
+
+        logging.info("Episode completed.")
+        for subscriber in self._subscribers:
+            subscriber.on_episode_end()
+
+    def _step(self) -> None:
+        """A single step of the runtime loop."""
+        observation = self._environment.get_observation()
+        action = self._agent.get_action(observation)
+        self._environment.apply_action(action)
+
+        for subscriber in self._subscribers:
+            subscriber.on_step(observation, action)
+
+        if self._environment.done():
+            self.stop()

packages/openpi-client/src/openpi_client/runtime/subscriber.py

@@ -0,0 +1,20 @@
+import abc
+
+
+class Subscriber(abc.ABC):
+    """Subscribes to events in the runtime.
+
+    Subscribers can be used to save data, visualize, etc.
+    """
+
+    @abc.abstractmethod
+    def on_episode_start(self) -> None:
+        """Called when an episode starts."""
+
+    @abc.abstractmethod
+    def on_step(self, observation: dict, action: dict) -> None:
+        """Append a step to the episode."""
+
+    @abc.abstractmethod
+    def on_episode_end(self) -> None:
+        """Called when an episode ends."""