imitation: Clean Imitation Learning Implementations

DALL·E - A robot watching a human dance on a mirror and mimicking his behavior as a reflection, digital art, trending on artstation

Abstract

imitation provides open-source implementations of imitation and reward learning algorithms in PyTorch. We include three inverse reinforcement learning (IRL) algorithms, three imitation learning algorithms and a preference comparison algorithm. The implementations have been benchmarked against previous results, and automated tests cover 98% of the code. Moreover, the algorithms are implemented in a modular fashion, making it simple to develop novel algorithms in the framework. Our source code, including documentation and examples, is available at https://github.com/HumanCompatibleAI/imitation

Juan Rocamonde
Juan Rocamonde
Research Fellow

My interests include AI, human language, knowledge systems, physics.