Diffail: Diffusion Adversarial Imitation Learning

Abstract

Imitation learning aims to solve the problem of defining reward functions in real-world decision-making tasks. The current popular approach is the Adversarial Imitation Learning (AIL) framework, which matches expert state-action occupancy measures to obtain a surrogate reward for forward reinforcement learning. However, the traditional discriminator is a simple binary classifier and doesn't learn an accurate distribution, which may result in failing to identify expert-level state-action pairs induced by the policy interacting with the environment. To address this issue, we propose a method named diffusion adversarial imitation learning (DiffAIL), which introduces the diffusion model into the AIL framework. Specifically, DiffAIL models the state-action pairs as unconditional diffusion models and uses diffusion loss as part of the discriminator's learning objective, which enables the discriminator to capture better expert demonstrations and improve generalization. Experimentally, the res

Stats

• citations6
• S2 citations—
• github stars24
• HF likes0
• heat score9.13
• arxiv keywang2023diffail

Related papers

• On Discovering Algorithms For Adversarial Imitation Learning (2025)0.00
• Provably Efficient Adversarial Imitation Learning With Unknown Transitions (2023)0.00
• RLIF: Interactive Imitation Learning As Reinforcement Learning (2023)0.00
• Non-adversarial Imitation Learning And Its Connections To Adversarial Methods (2020)0.00
• State-only Imitation With Transition Dynamics Mismatch (2020)0.00
• Don't Start From Scratch: Behavioral Refinement Via Interpolant-based Policy Diffusion (2024)9.28
• Extrinsicaly Rewarded Soft Q Imitation Learning With Discriminator (2024)0.00
• IDQL: Implicit Q-learning As An Actor-critic Method With Diffusion Policies (2023)0.00