Invalidate the cache if it is expired. Return True if the cache was invalidated.

A single step of the runtime loop.

Update KV cache with new values

Update histograms with new vectors.

Take an action in the environment.

Create a dataset for training.

Create a default policy for the given environment.

Create a policy from the given arguments.

Converts a string like "B" or "B/32" into a params dict.

Deserialize the running statistics from a JSON string.

Detect available cameras in the HDF5 files.

Query the agent for the next action.

Query the environment for the current state.

Infer actions from observations.

Custom logging format for better readability.

Allow the environment to signal that the episode is complete. This will be called after each step. It should return `True` if the episode is

Converts input from left-align to right-aligned.

Marks the end of an episode.

Called when an episode ends.

Called when an episode starts.

Append a step to the episode.

Computes sine-cosine positional embedding vectors for scalar positions.

Follows the MoCo v3 logic.

Temporarily prevent keyboard interrupts by delaying them until after the protected code.

Like np.put_along_axis(..., axis=-1), since jax is missing it.

Serialize the running statistics to a JSON string.

Convert the Observation to a nested dict.

Transform the dataset by applying the data transforms.

Converts a PyTree into a human-readable string for logging. Optionally, `interp_func` can be provided to convert the leaf values to more meaningfu

Factory function, because linen really don't like what I'm doing!

Apply transformation to the data. Args: data: The data to apply the transform to. This is a possibly nested dictionary that conta

Create a group.

Applies the AddPositionEmbs module. Args: inputs: Inputs to the layer. Returns: Output tensor with shape `(bs, t

Applies Transformer MlpBlock module.

Applies Encoder1DBlock module. Args: inputs: Inputs to the layer. deterministic: Dropout will not be applied when set to