Research map / Reinforcement learning / Imitation learning
DPAIL: Training Diffusion Policy for Adversarial Imitation Learning without Policy Optimization
Read the paperCheck your idea against 108,967 papers
AI-extracted summary. Written by AI from the paper's abstract only. Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Proposes DPAIL, an adversarial imitation learning framework that uses diffusion policies to capture multi-modal expert demonstrations.
Problem
Traditional adversarial imitation learning collapses multi-modal expert behaviors into a single strategy, failing to replicate the diverse strategies of human experts.
Approach
Leverages diffusion models as the policy within an adversarial imitation learning framework so that multi-modal demonstrations are represented, and training avoids conventional policy optimization (per the title).
Experimental setup
Builds on: adversarial imitation learning diffusion models
Closest papers by meaning
- DiffAIL: Diffusion Adversarial Imitation Learning (AAAI 2024 · similarity 0.92)
- Diffusion Imitation from Observation (NeurIPS 2024 · similarity 0.91)
- Diffusing States and Matching Scores: A New Framework for Imitation Learning (ICLR 2025 · similarity 0.91)
- Diffusion-Reward Adversarial Imitation Learning (NeurIPS 2024 · similarity 0.90)
- Exploring Gradient Explosion in Generative Adversarial Imitation Learning: A Probabilistic Perspective (AAAI 2024 · similarity 0.89)
- Diffusion Policy Attacker: Crafting Adversarial Attacks for Diffusion-based Policies (NeurIPS 2024 · similarity 0.89)
Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.