Evaluation server

Run a GR00T policy as a server for distributed inference and evaluation

The evaluation server script (gr00t/eval/run_gr00t_server.py) runs a policy as a network server, allowing multiple clients to send observations and receive actions over TCP.

Usage

python gr00t/eval/run_gr00t_server.py \
  --model-path checkpoints/checkpoint-5000 \
  --embodiment-tag GR1 \
  --device cuda \
  --host 0.0.0.0 \
  --port 5555

Parameters

Policy configuration

model-path · str · default: "None"

Path to the model checkpoint directory for GR00T policy inference.

Either model-path or dataset-path must be provided.

embodiment-tag · EmbodimentTag · default: "NEW_EMBODIMENT"

Embodiment tag identifying the robot configuration. See embodiment tags.

device · str · default: "cuda"

Device to run the model on: cuda, cuda:0, cuda:1, or cpu.

Replay policy configuration

dataset-path · str · default: "None"

Path to a dataset for replay policy (replays recorded trajectories instead of running inference).

Use this for debugging or baseline comparisons.

modality-config-path · str · default: "None"

Path to a JSON file containing modality configuration for replay policy.

If not provided, uses default configuration from MODALITY_CONFIGS[embodiment_tag].

execution-horizon · int · default: "None"

Policy execution horizon during inference. If specified, overrides the default horizon.

Server configuration

host · str · default: "0.0.0.0"

Host address for the server. Use 0.0.0.0 to accept connections from any network interface.

port · int · default: "5555"

Port number for the server to listen on.

strict · bool · default: "True"

Whether to enforce strict input and output validation. Recommended to keep enabled for production.

use-sim-policy-wrapper · bool · default: "False"

Whether to wrap the policy with Gr00tSimPolicyWrapper for simulation-specific processing.

Enable this when serving policies for simulation environments.

Example workflows

Serve a GR00T policy

python gr00t/eval/run_gr00t_server.py \
  --model-path checkpoints/checkpoint-5000 \
  --embodiment-tag GR1 \
  --device cuda:0 \
  --port 5555

Output:

Starting GR00T inference server...
  Embodiment tag: GR1
  Model path: checkpoints/checkpoint-5000
  Device: cuda:0
  Host: 0.0.0.0
  Port: 5555
Server running on 0.0.0.0:5555

Serve for simulation

python gr00t/eval/run_gr00t_server.py \
  --model-path checkpoints/gr1_sim_model \
  --embodiment-tag GR1 \
  --use-sim-policy-wrapper \
  --port 5555

Serve a replay policy

python gr00t/eval/run_gr00t_server.py \
  --dataset-path datasets/recorded_demos \
  --embodiment-tag GR1 \
  --modality-config-path configs/gr1_modalities.json \
  --execution-horizon 16

Multi-GPU setup

Run multiple servers on different GPUs:

# GPU 0
python gr00t/eval/run_gr00t_server.py \
  --model-path checkpoints/checkpoint-5000 \
  --device cuda:0 \
  --port 5555

# GPU 1
python gr00t/eval/run_gr00t_server.py \
  --model-path checkpoints/checkpoint-5000 \
  --device cuda:1 \
  --port 5556

Client usage

Connect to the server using PolicyClient:

from gr00t.policy.server_client import PolicyClient

# Create client
policy = PolicyClient(host="127.0.0.1", port=5555)

# Get action
observation = {
    "video": {"camera_0": image_array},
    "state": {"joint_positions": joint_array},
    "language": {"instruction": [["pick up the cup"]]}
}
action, metadata = policy.get_action(observation)

With open-loop evaluation

# Terminal 1: Start server
python gr00t/eval/run_gr00t_server.py \
  --model-path checkpoints/checkpoint-5000 \
  --port 5555

# Terminal 2: Run open-loop eval
python gr00t/eval/open_loop_eval.py \
  --host 127.0.0.1 \
  --port 5555 \
  --dataset-path demo_data/cube_to_bowl_5/

With closed-loop evaluation

# Terminal 1: Start server
python gr00t/eval/run_gr00t_server.py \
  --model-path checkpoints/checkpoint-5000 \
  --use-sim-policy-wrapper \
  --port 5555

# Terminal 2: Run closed-loop eval
python gr00t/eval/rollout_policy.py \
  --env-name gr1_unified/PnPCanToDrawerClose_GR1ArmsAndWaistFourierHands_Env \
  --policy-client-host 127.0.0.1 \
  --policy-client-port 5555 \
  --n-episodes 50

Policy types

Gr00tPolicy

Loaded when model-path is provided:

• Runs transformer-based policy inference
• Supports all GR00T embodiments
• GPU-accelerated
• Configurable via embodiment-tag and device

ReplayPolicy

Loaded when dataset-path is provided:

• Replays actions from recorded demonstrations
• Useful for testing data collection pipelines
• Configurable via modality-config-path and execution-horizon

Server protocol

The server implements a simple request-response protocol:

1. Client sends observation dictionary
2. Server runs policy inference
3. Server returns action dictionary and metadata

The PolicyServer class handles:

• TCP socket management
• Request serialization/deserialization
• Multi-client support (sequential processing)
• Graceful shutdown on KeyboardInterrupt

Performance considerations

• Single client per server: The server processes requests sequentially. For parallel inference, run multiple servers on different ports/GPUs.
• Batch size: Each request processes a single observation. For higher throughput, use local policy inference instead.
• Network latency: Server adds network overhead. For real-time applications, consider deploying on the same machine as the client.

The server does NOT authenticate clients. Only run on trusted networks or add authentication if deploying in production.

Troubleshooting

Port already in use

Address already in use: 0.0.0.0:5555

Change the port:

python gr00t/eval/run_gr00t_server.py --port 5556

Model path not found

FileNotFoundError: Model path checkpoints/checkpoint-5000 does not exist

Verify the checkpoint directory exists and contains model files.

CUDA out of memory

RuntimeError: CUDA out of memory

Reduce batch size, use a smaller model, or switch to CPU:

python gr00t/eval/run_gr00t_server.py --device cpu