Spaces:
Sleeping
Sleeping
File size: 3,110 Bytes
53022c7 fe7b890 53022c7 |
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 |
# Copyright (c) Meta Platforms, Inc. and affiliates.
# All rights reserved.
#
# This source code is licensed under the BSD-style license found in the
# LICENSE file in the root directory of this source tree.
"""Gpu Mode Environment Client."""
from typing import Dict
from openenv.core.client_types import StepResult
from openenv.core.env_server.types import State
from openenv.core import EnvClient
from .models import GpuModeAction, GpuModeObservation
class GpuModeEnv(EnvClient[GpuModeAction, GpuModeObservation, State]):
"""
Client for the Gpu Mode Environment.
This client maintains a persistent WebSocket connection to the environment server,
enabling efficient multi-step interactions with lower latency.
Each client instance has its own dedicated environment session on the server.
Example:
>>> # Connect to a running server
>>> with GpuModeEnv(base_url="http://localhost:8000") as client:
... result = client.reset()
... print(result.observation.echoed_message)
...
... result = client.step(GpuModeAction(message="Hello!"))
... print(result.observation.echoed_message)
Example with Docker:
>>> # Automatically start container and connect
>>> client = GpuModeEnv.from_docker_image("gpu_mode-env:latest")
>>> try:
... result = client.reset()
... result = client.step(GpuModeAction(message="Test"))
... finally:
... client.close()
"""
def _step_payload(self, action: GpuModeAction) -> Dict:
"""
Convert GpuModeAction to JSON payload for step message.
Args:
action: GpuModeAction instance
Returns:
Dictionary representation suitable for JSON encoding
"""
return {
"message": action.message,
}
def _parse_result(self, payload: Dict) -> StepResult[GpuModeObservation]:
"""
Parse server response into StepResult[GpuModeObservation].
Args:
payload: JSON response data from server
Returns:
StepResult with GpuModeObservation
"""
obs_data = payload.get("observation", {})
observation = GpuModeObservation(
echoed_message=obs_data.get("echoed_message", ""),
message_length=obs_data.get("message_length", 0),
done=payload.get("done", False),
reward=payload.get("reward"),
metadata=obs_data.get("metadata", {}),
)
return StepResult(
observation=observation,
reward=payload.get("reward"),
done=payload.get("done", False),
)
def _parse_state(self, payload: Dict) -> State:
"""
Parse server response into State object.
Args:
payload: JSON response from state request
Returns:
State object with episode_id and step_count
"""
return State(
episode_id=payload.get("episode_id"),
step_count=payload.get("step_count", 0),
)
|