Improving Long-Horizon Imitation Through Instruction Prediction
This addresses challenges in learning-based agents for complex reasoning tasks, though it is incremental by building on transformer-based models.
The paper tackles the problem of long-horizon planning in low-data regimes by using language-based instruction prediction as auxiliary supervision, resulting in significant performance improvements on BabyAI and Crafter benchmarks with limited demonstrations.
Complex, long-horizon planning and its combinatorial nature pose steep challenges for learning-based agents. Difficulties in such settings are exacerbated in low data regimes where over-fitting stifles generalization and compounding errors hurt accuracy. In this work, we explore the use of an often unused source of auxiliary supervision: language. Inspired by recent advances in transformer-based models, we train agents with an instruction prediction loss that encourages learning temporally extended representations that operate at a high level of abstraction. Concretely, we demonstrate that instruction modeling significantly improves performance in planning environments when training with a limited number of demonstrations on the BabyAI and Crafter benchmarks. In further analysis we find that instruction modeling is most important for tasks that require complex reasoning, while understandably offering smaller gains in environments that require simple plans. More details and code can be found at https://github.com/jhejna/instruction-prediction.