SD2AIL: Adversarial Imitation Learning from Synthetic Demonstrations via Diffusion Models
By: Pengcheng Li , Qiang Fang , Tong Zhao and more
Adversarial Imitation Learning (AIL) is a dominant framework in imitation learning that infers rewards from expert demonstrations to guide policy optimization. Although providing more expert demonstrations typically leads to improved performance and greater stability, collecting such demonstrations can be challenging in certain scenarios. Inspired by the success of diffusion models in data generation, we propose SD2AIL, which utilizes synthetic demonstrations via diffusion models. We first employ a diffusion model in the discriminator to generate synthetic demonstrations as pseudo-expert data that augment the expert demonstrations. To selectively replay the most valuable demonstrations from the large pool of (pseudo-) expert demonstrations, we further introduce a prioritized expert demonstration replay strategy (PEDR). The experimental results on simulation tasks demonstrate the effectiveness and robustness of our method. In particular, in the Hopper task, our method achieves an average return of 3441, surpassing the state-of-the-art method by 89. Our code will be available at https://github.com/positron-lpc/SD2AIL.
Similar Papers
Near-Optimal Second-Order Guarantees for Model-Based Adversarial Imitation Learning
Machine Learning (CS)
Teaches robots to learn from watching, faster.
Limitation Learning: Catching Adverse Dialog with GAIL
Computation and Language
Teaches computers to talk like people.
TubeDAgger: Reducing the Number of Expert Interventions with Stochastic Reach-Tubes
Systems and Control
Teaches robots to learn from mistakes better.