Provable Hierarchical Imitation Learning Via EM

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 prim

Stats

• citations0
• S2 citations—
• github stars0
• HF likes0
• heat score0.00
• arxiv keyzhang2020provable

Related papers

• Discovering Hierarchies Using Imitation Learning From Hierarchy Aware Policies (2018)0.00
• A Provably Efficient Option-based Algorithm For Both High-level And Low-level Learning (2024)0.00
• Hyperbolic Embeddings For Learning Options In Hierarchical Reinforcement Learning (2018)0.00
• Hierarchical Reinforcement Learning Via Advantage-weighted Information Maximization (2019)0.00
• Hindsight Expectation Maximization For Goal-conditioned Reinforcement Learning (2020)0.00
• A Bayesian Solution To The Imitation Gap (2024)0.00
• Toward The Fundamental Limits Of Imitation Learning (2020)0.00
• Hyperparameter Selection For Imitation Learning (2021)0.00