The summary says they use text and a search for “text” in the paper gives this on page 32:
“In these past works, the goal usually consists of the position of the agent or a target observation to reach, however some previous work uses text goals (Colas et al., 2020) for the agent similarly to this work.”
So I thought they provided goals as text. I’ll be disappointed if they don’t. Hopefully, future work will do so (and potentially use pretrained LMs to process the goal texts).
What’s the practical difference between “text” and one-hots of said “text”? One-hots are the standard for inputting text into models. It is only recently that we expect models to learn their preferred encoding for raw text (cf. transformers). By taking a small shortcut, the authors of this paper get to show off their agent work without loss of generality: one could still give one-hot instructions to an agent that is learning to act in the real life.
[Deleted]
The summary says they use text and a search for “text” in the paper gives this on page 32:
“In these past works, the goal usually consists of the position of the agent or a target observation to reach, however some previous work uses text goals (Colas et al., 2020) for the agent similarly to this work.”
So I thought they provided goals as text. I’ll be disappointed if they don’t. Hopefully, future work will do so (and potentially use pretrained LMs to process the goal texts).
[Deleted]
What’s the practical difference between “text” and one-hots of said “text”? One-hots are the standard for inputting text into models. It is only recently that we expect models to learn their preferred encoding for raw text (cf. transformers). By taking a small shortcut, the authors of this paper get to show off their agent work without loss of generality: one could still give one-hot instructions to an agent that is learning to act in the real life.