Primal Wasserstein Imitation Learning

Abstract

Imitation Learning (IL) methods seek to match the behavior of an agent with that of an expert. In the present work, we propose a new IL method based on a conceptually simple algorithm: Primal Wasserstein Imitation Learning (PWIL), which ties to the primal form of the Wasserstein distance between the expert and the agent state-action distributions. We present a reward function which is derived offline, as opposed to recent adversarial IL algorithms that learn a reward function through interactions with the environment, and which requires little fine-tuning. We show that we can recover expert behavior on a variety of continuous control tasks of the MuJoCo domain in a sample efficient manner in terms of agent interactions and of expert interactions with the environment. Finally, we show that the behavior of the agent we train matches the behavior of the expert with the Wasserstein distance, rather than the commonly used proxy of performance.

Stats

• citations0
• S2 citations—
• github stars0
• HF likes0
• heat score0.00
• arxiv keydadashi2020primal

Related papers

• Imitation Learning From Observation Through Optimal Transport (2023)2.26
• Proximal Point Imitation Learning (2022)0.00
• State-only Imitation With Transition Dynamics Mismatch (2020)0.00
• Co-imitation Learning Without Expert Demonstration (2021)0.00
• A New Framework For Query Efficient Active Imitation Learning (2019)0.00
• On Discovering Algorithms For Adversarial Imitation Learning (2025)0.00
• Continuous Mean-zero Disagreement-regularized Imitation Learning (CMZ-DRIL) (2024)0.00
• Mimicking Better By Matching The Approximate Action Distribution (2023)0.00