WeightReceiver

class torchrl.weight_update.WeightReceiver(scheme: WeightSyncScheme)

Receives weights for ONE model in ONE worker.

Created and managed by WeightSyncScheme. Users should not instantiate directly.

apply_weights(weights: Any) → None

Apply received weights to registered model (legacy).

Parameters:

weights – The weights to apply.

Note

This is the legacy method. Use receive() in the worker loop instead.

receive(timeout: float = 0.001) → bool

Check for and apply new weights (non-blocking).

This method is called in the worker’s main loop to check if new weights have been sent. If weights are available, they are applied to the registered model immediately.

Parameters:

timeout – Maximum time to wait for weights (seconds). Use 0 for immediate return.

Returns:

True if weights were received and applied False if no weights were available

Note: For SharedMemWeightSyncScheme, this always returns False since workers automatically see updates via shared memory.