newton.actuators.ControllerNeuralMLP

class newton.actuators.ControllerNeuralMLP(model_path)

Bases: Controller

MLP-based neural network controller.

Uses a pre-trained MLP to compute joint effort from concatenated, scaled position-error and joint-velocity history. The output is multiplied by effort_scale to convert from network units to physical effort [N or N·m].

Configuration parameters (input_order, input_idx, pos_scale, vel_scale, effort_scale) are read from checkpoint metadata, falling back to defaults when absent. .onnx checkpoints run through Warp-NN. Torch checkpoints keep the Torch backend and accept pt2 archives (.pt2 saved with torch.export.save; preferred) and the deprecated TorchScript (.pt saved with torch.jit.save) and module-bundle ({"model": <network module>, "metadata": {...}} saved with torch.save) formats.

classmethod resolve_arguments(args)

__init__(model_path)

Initialize MLP controller from a checkpoint file.

Parameters:

model_path (str) – Path to the .onnx, .pt2, .pt, or .pth checkpoint.

compute(positions, velocities, target_pos, target_vel, feedforward, pos_indices, vel_indices, target_pos_indices, target_vel_indices, forces, state, dt, device=None)

finalize(device, num_actuators)

is_graphable()

is_stateful()

state(num_actuators, device)

update_state(current_state, next_state)

SHARED_PARAMS: ClassVar[set[str]] = {'model_path'}