CompILE: Compositional Imitation Learning and Execution
This addresses the challenge of compositional imitation learning for hierarchical agents in robotics and AI, though it appears incremental as it builds on existing imitation and hierarchical learning methods.
The paper tackles the problem of learning reusable, hierarchical behavior segments from demonstrations, introducing CompILE, which uses unsupervised sequence segmentation to generalize to longer sequences and unseen environments, achieving correct task boundaries and enabling learning with sparse rewards.
We introduce Compositional Imitation Learning and Execution (CompILE): a framework for learning reusable, variable-length segments of hierarchically-structured behavior from demonstration data. CompILE uses a novel unsupervised, fully-differentiable sequence segmentation module to learn latent encodings of sequential data that can be re-composed and executed to perform new tasks. Once trained, our model generalizes to sequences of longer length and from environment instances not seen during training. We evaluate CompILE in a challenging 2D multi-task environment and a continuous control task, and show that it can find correct task boundaries and event encodings in an unsupervised manner. Latent codes and associated behavior policies discovered by CompILE can be used by a hierarchical agent, where the high-level policy selects actions in the latent code space, and the low-level, task-specific policies are simply the learned decoders. We found that our CompILE-based agent could learn given only sparse rewards, where agents without task-specific policies struggle.