Add per node beam size option to beam search

[epwalsh]

I added an option to the beam search classes called per_node_beam_size, which sets the maximum number of candidates to consider, at each step, from the same action history. In vanilla beam search, per_node_beam_size = beam_size, which is left as the default behavior. As discovered in Beam Search Strategies for Neural Machine Translation, setting per_node_beam_size to a value smaller than beam_size can result in better predictions, as it introduces more diversity into the search.

[epwalsh]

For some reason this file had executable permissions, so I just chmod -x'ed it

[matt-gardner]

Thanks for this, LGTM.