Language

unilab.algos.torch.offpolicy.worker.sample_offpolicy_actions¶

unilab.algos.torch.offpolicy.worker.sample_offpolicy_actions(actor, algo_type, obs_torch, prev_dones_torch, priv_info_torch=None)[source]¶

Sample collector actions using the algorithm’s exploration policy.

Parameters:

algo_type (str)
obs_torch (Tensor)
prev_dones_torch (Tensor)
priv_info_torch (Tensor | None)

Return type:

Tensor