Pre-Learning Environment Representations for Data-Efficient Neural Instruction Following

However, neural networks' powerful abilities to induce complex representations have come at the cost of data efficiency. Indeed, compared to earlier logical form-based methods, neural networks can sometimes require orders of magnitude more data. The data-hungriness of neural approaches is not surprising - starting with classic logical forms improves data efficiency by presenting a system with pre-made abstractions, where end-to-end neural approaches must do the hard work of inducing abstractions on their own. In this paper, we aim to combine the power of neural networks with the data-efficiency of logical forms by pre-learning abstractions in a semi-supervised way, satiating part of the network's data hunger on cheaper unlabeled data from the environment. When neural nets have only limited data that Figure 1: After seeing this transition, a neural net might generalize this action as stack red blocks to the right of blue blocks except for on brown blocks, but a generalization like stack red blocks on orange blocks is more plausible and generally applicable. We aim to guide our model towards more plausible generalizations by pre-learning inductive biases from observations of the environment.