LocoMuJoCo: A Comprehensive Imitation Learning Benchmark for Locomotion

TL;DR

LocoMuJoCo introduces a diverse, realistic locomotion benchmark with comprehensive datasets and evaluation tools to advance imitation learning research in complex, real-world scenarios.

Contribution

It provides a new, comprehensive benchmark with diverse environments, datasets, and evaluation metrics for imitation learning in locomotion tasks.

Findings

Benchmark includes quadrupeds, bipeds, and human models.

Provides datasets with real noisy motion capture data.

Includes baseline algorithms for comparison.

Abstract

Imitation Learning (IL) holds great promise for enabling agile locomotion in embodied agents. However, many existing locomotion benchmarks primarily focus on simplified toy tasks, often failing to capture the complexity of real-world scenarios and steering research toward unrealistic domains. To advance research in IL for locomotion, we present a novel benchmark designed to facilitate rigorous evaluation and comparison of IL algorithms. This benchmark encompasses a diverse set of environments, including quadrupeds, bipeds, and musculoskeletal human models, each accompanied by comprehensive datasets, such as real noisy motion capture data, ground truth expert data, and ground truth sub-optimal data, enabling evaluation across a spectrum of difficulty levels. To increase the robustness of learned agents, we provide an easy interface for dynamics randomization and offer a wide range of partially observable tasks to train agents across different embodiments. Finally, we provide handcrafted metrics for each task and ship our benchmark with state-of-the-art baseline algorithms to ease evaluation and enable fast benchmarking.