Provable Hierarchical Imitation Learning via EM
arXiv:2010.03133
Abstract
Due to recent empirical successes, the options framework for hierarchical reinforcement learning is gaining increasing popularity. Rather than learning from rewards which suffers from the curse of dimensionality, we consider learning an options-type hierarchical policy from expert demonstrations. Such a problem is referred to as hierarchical imitation learning. Converting this problem to parameter inference in a latent variable model, we theoretically characterize the EM approach proposed by Daniel et al. (2016). The population level algorithm is analyzed as an intermediate step, which is nontrivial due to the samples being correlated. If the expert policy can be parameterized by a variant of the options framework, then under regularity conditions, we prove that the proposed algorithm converges with high probability to a norm ball around the true parameter. To our knowledge, this is the first performance guarantee for an hierarchical imitation learning algorithm that only observes primitive state-action pairs.
arXiv commentTo appear in AISTATS 2021
References in corpus (9)
- Hierarchical Deep Reinforcement Learning: Integrating Temporal Abstraction and Intrinsic Motivation
- FeUdal Networks for Hierarchical Reinforcement Learning
- Data-Efficient Hierarchical Reinforcement Learning
- Multi-Level Discovery of Deep Options
- Global analysis of Expectation Maximization for mixtures of two Gaussians
- Regularized EM Algorithms: A Unified Framework and Statistical Guarantees
- TACO: Learning Task Decomposition via Temporal Alignment for Control
- Exploration--Exploitation in MDPs with Options
- Singularity, Misspecification, and the Convergence Rate of EM