Research map / Reinforcement learning / Imitation learning
Robust Imitation of Diverse Behaviors
Read the paperCheck your idea against 108,967 papers
AI-extracted summary. Written by AI from the paper's title only (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Measured effects reported in the paper
| What was changed | Where | Measured | Effect |
|---|---|---|---|
| Add conditional adversarial fine-tuning to the VAE behavioral-cloning policy | VAE policy · 2D Walker | absolute average-speed difference | Helped |
| Add conditional adversarial fine-tuning to the VAE behavioral-cloning policy | VAE policy · 62 DoF humanoid | fall rate before episode end | Helped |
| Use VAE behavioral cloning without adversarial fine-tuning (ablation) | Diverse imitation approach · 2D Walker | imitation quality | Hurt |
| Remove latent-embedding conditioning (ablation) | GAIL · 2D Walker | behavior diversity | Hurt |
| Use unconditioned GAIL instead of conditioning on VAE embeddings (ablation) | GAIL · 2D Walker | trajectory coherence | Hurt |
| Use the VAE policy without adversarial fine-tuning (ablation) | Diverse imitation approach · 62 DoF humanoid | controller robustness | Hurt |
Closest papers by meaning
- Visual Adversarial Imitation Learning using Variational Models (NeurIPS 2021 · similarity 0.90)
- A Bayesian Approach to Generative Adversarial Imitation Learning (NeurIPS 2018 · similarity 0.90)
- Imitation Learning via Kernel Mean Embedding (AAAI 2018 · similarity 0.89)
- Exploring Gradient Explosion in Generative Adversarial Imitation Learning: A Probabilistic Perspective (AAAI 2024 · similarity 0.89)
- Noise-conditioned Energy-based Annealed Rewards (NEAR): A Generative Framework for Imitation Learning from Observation (ICLR 2025 · similarity 0.89)
- Imitation from Observations with Trajectory-Level Generative Embeddings (NeurIPS 2026 · similarity 0.88)
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.