Towards Diverse Behaviors: A Benchmark for Imitation Learning with Human Demonstrations

TL;DR

This paper introduces a new benchmark and datasets for evaluating imitation learning algorithms on their ability to learn and reproduce diverse, multi-modal human behaviors in complex, multi-object manipulation tasks, addressing a key challenge in the field.

Contribution

The work presents simulation environments, datasets, and metrics specifically designed to evaluate and quantify a model's capacity to learn diverse human behaviors in imitation learning.

Findings

State-of-the-art methods show limited ability to capture behavior diversity.

The proposed metrics provide meaningful insights into model robustness and versatility.

Benchmark results highlight gaps and future directions for imitation learning algorithms.

Abstract

Imitation learning with human data has demonstrated remarkable success in teaching robots in a wide range of skills. However, the inherent diversity in human behavior leads to the emergence of multi-modal data distributions, thereby presenting a formidable challenge for existing imitation learning algorithms. Quantifying a model's capacity to capture and replicate this diversity effectively is still an open problem. In this work, we introduce simulation benchmark environments and the corresponding Datasets with Diverse human Demonstrations for Imitation Learning (D3IL), designed explicitly to evaluate a model's ability to learn multi-modal behavior. Our environments are designed to involve multiple sub-tasks that need to be solved, consider manipulation of multiple objects which increases the diversity of the behavior and can only be solved by policies that rely on closed loop sensory feedback. Other available datasets are missing at least one of these challenging properties. To address the challenge of diversity quantification, we introduce tractable metrics that provide valuable insights into a model's ability to acquire and reproduce diverse behaviors. These metrics offer a practical means to assess the robustness and versatility of imitation learning algorithms. Furthermore, we conduct a thorough evaluation of state-of-the-art methods on the proposed task suite. This evaluation serves as a benchmark for assessing their capability to learn diverse behaviors. Our findings shed light on the effectiveness of these methods in tackling the intricate problem of capturing and generalizing multi-modal human behaviors, offering a valuable reference for the design of future imitation learning algorithms.