Research map / Reinforcement learning / Imitation learning
IQ-Learn: Inverse soft-Q Learning for Imitation
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 |
|---|---|---|---|
| replace the strongest listed baseline with IQ-Learn | MuJoCo imitation learning from one expert trajectory · Hopper | environment return: 3312.1 -> 3546.4 | Helped |
| replace the strongest listed baseline with IQ-Learn | MuJoCo imitation learning from one expert trajectory · Half-Cheetah | environment return: 4080.6 -> 5076.6 | Helped |
| replace the strongest listed baseline with IQ-Learn | MuJoCo imitation learning from one expert trajectory · Walker | environment return: 4107.9 -> 5134.0 | Helped |
| replace the strongest listed baseline with IQ-Learn | MuJoCo imitation learning from one expert trajectory · Ant | environment return: 2299.1 -> 4362.9 | Helped |
| replace the strongest listed baseline with IQ-Learn | MuJoCo imitation learning from one expert trajectory · Humanoid | environment return: 644.5 -> 5227.1 | Helped |
| use Jensen-Shannon, Hellinger, or chi-square divergence instead of KL divergence (ablation) | IQ-Learn offline IL · LunarLander | environment return | Helped |
| use target updates during Q-learning (ablation) | IQ-Learn · MuJoCo | environment return | Helped |
| estimate the online value term using replay samples rather than only initial states (ablation) | IQ-Learn online training · online IL | training stability | Helped |
Closest papers by meaning
- Reward-free World Models for Online Imitation Learning (ICML 2025 · similarity 0.92)
- Inverse Factorized Soft Q-Learning for Cooperative Multi-agent Imitation Learning (NeurIPS 2024 · similarity 0.91)
- Imitating Language via Scalable Inverse Reinforcement Learning (NeurIPS 2024 · similarity 0.90)
- Hybrid Inverse Reinforcement Learning (ICML 2024 · similarity 0.90)
- Is Behavior Cloning All You Need? Understanding Horizon in Imitation Learning (NeurIPS 2024 · similarity 0.90)
- Rethinking Inverse Reinforcement Learning: from Data Alignment to Task Alignment (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.