Research map / Multi-agent systems and games / Cooperative multi-agent RL
Multi-Agent Imitation by Learning and Sampling from Factorized Soft Q-Function
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 a multi-agent imitation learning method that learns a factorized soft Q-function and samples actions from it, aiming to avoid BC's compounding errors and AIL's adversarial instability.
Problem
Multi-agent imitation learning (MAIL) from expert demonstrations, where behavior cloning suffers compounding errors and adversarial imitation learning is unstable.
Approach
Learns a factorized soft Q-function for multi-agent imitation and samples actions from it, avoiding adversarial optimization; details beyond the abstract are not available.
Experimental setup
Baselines: Behavior Cloning Adversarial Imitation Learning
Closest papers by meaning
- Inverse Factorized Soft Q-Learning for Cooperative Multi-agent Imitation Learning (NeurIPS 2024 · similarity 0.92)
- IQ-Learn: Inverse soft-Q Learning for Imitation (NeurIPS 2021 · similarity 0.90)
- Split the Differences, Pool the Rest: Provably Efficient Multi-Objective Imitation (NeurIPS 2026 · similarity 0.87)
- Reward-free World Models for Online Imitation Learning (ICML 2025 · similarity 0.87)
- Provably and Practically Efficient Adversarial Imitation Learning with General Function Approximation (NeurIPS 2024 · similarity 0.86)
- Deep Implicit Imitation Reinforcement Learning in Heterogeneous Action Settings (AAAI 2025 · similarity 0.86)
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.