Method get_logprobs_subsample

Calculating the logprobs of random samples of denoised chains. Args: cond: dict with key state/rgb; more recent obs at the end state: (B, To, Do) rgb: (B, To, C, H, W) chains: (B, K+1, Ta, Da) get_ent: flag for ret

(
        self,
        cond,
        chains_prev,
        chains_next,
        denoising_inds,
        get_ent: bool = False,
        use_base_policy: bool = False,
    )