# CoMI-IRL: Contrastive Multi-Intention Inverse Reinforcement Learning

arXiv: https://arxiv.org/abs/2602.07496 · HTML: https://mlsanity.com/paper/2602.07496/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Placed in Inverse reinforcement learning, one of 13 directions in Offline RL and imitation learning from data.
- Builds on 31 of its 61 references that are in the map.
- First posted on arXiv 7 Feb 2026.

## Placed in

- Offline RL and imitation learning from data / [Inverse reinforcement learning](https://mlsanity.com/offlinerl/inverse-reinforcement-learning/)

## Builds on (most cited first, 30 of 31)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding](https://mlsanity.com/paper/1810.04805/) (2018)
- [A Simple Framework for Contrastive Learning of Visual Representations](https://mlsanity.com/paper/2002.05709/) (2020)
- [Representation Learning with Contrastive Predictive Coding](https://mlsanity.com/paper/1807.03748/) (2018)
- [UMAP: Uniform Manifold Approximation and Projection for Dimension Reduction](https://mlsanity.com/paper/1802.03426/) (2018)
- [Fourier Features Let Networks Learn High Frequency Functions in Low Dimensional Domains](https://mlsanity.com/paper/2006.10739/) (2020)
- [SimCSE: Simple Contrastive Learning of Sentence Embeddings](https://mlsanity.com/paper/2104.08821/) (2021)
- [Generative Adversarial Imitation Learning](https://mlsanity.com/paper/1606.03476/) (2016)
- [Decision Transformer: Reinforcement Learning via Sequence Modeling](https://mlsanity.com/paper/2106.01345/) (2021)
- [Understanding Contrastive Representation Learning through Alignment and Uniformity on the Hypersphere](https://mlsanity.com/paper/2005.10242/) (2020)
- [On the Spectral Bias of Neural Networks](https://mlsanity.com/paper/1806.08734/) (2018)
- [Learning deep representations by mutual information estimation and maximization](https://mlsanity.com/paper/1808.06670/) (2018)
- [Learning Robust Rewards with Adversarial Inverse Reinforcement Learning](https://mlsanity.com/paper/1710.11248/) (2017)
- [From Louvain to Leiden: guaranteeing well-connected communities](https://mlsanity.com/paper/1810.08473/) (2018)
- [A Connection between Generative Adversarial Networks, Inverse Reinforcement Learning, and Energy-Based Models](https://mlsanity.com/paper/1611.03852/) (2016)
- [Representational Strengths and Limitations of Transformers](https://mlsanity.com/paper/2306.02896/) (2023)
- [Learnable Fourier Features for Multi-Dimensional Spatial Positional Encoding](https://mlsanity.com/paper/2106.02795/) (2021)
- [Multi-Modal Imitation Learning from Unstructured Demonstrations using Generative Adversarial Nets](https://mlsanity.com/paper/1705.10479/) (2017)
- [Self-attention with Functional Time Representation Learning](https://mlsanity.com/paper/1911.12864/) (2019)
- [Contrastive Trajectory Similarity Learning with Dual-Feature Attention](https://mlsanity.com/paper/2210.05155/) (2022)
- [[CLS] Token Tells Everything Needed for Training-free Efficient MLLMs](https://mlsanity.com/paper/2412.05819/) (2024)
- [The NLP Task Effectiveness of Long-Range Transformers](https://mlsanity.com/paper/2202.07856/) (2022)
- [Learning Options via Compression](https://mlsanity.com/paper/2212.04590/) (2022)
- [Trading Positional Complexity vs. Deepness in Coordinate Networks](https://mlsanity.com/paper/2205.08987/) (2022)
- [Strongly Augmented Contrastive Clustering](https://mlsanity.com/paper/2206.00380/) (2022)
- [Deep Adaptive Multi-Intention Inverse Reinforcement Learning](https://mlsanity.com/paper/2107.06692/) (2021)
- [Inverse Reinforce Learning with Nonparametric Behavior Clustering](https://mlsanity.com/paper/1712.05514/) (2017)
- [On Learning Informative Trajectory Embeddings for Imitation, Classification and Regression](https://mlsanity.com/paper/2501.09327/) (2025)
- [Contrast & Compress: Learning Lightweight Embeddings for Short Trajectories](https://mlsanity.com/paper/2506.02571/) (2025)
- [LiMIIRL: Lightweight Multiple-Intent Inverse Reinforcement Learning](https://mlsanity.com/paper/2106.01777/) (2021)

## Built on by (most cited first, 2 of 2)

- [ConTraIRL: Factorized Contrastive Abstractions for Transferable IRL](https://mlsanity.com/paper/2606.03017/) (2026)
- [Objective-Behavior Alignment: Diagnostics for MORL Policy Selection](https://mlsanity.com/paper/2606.21321/) (2026)

## Abstract (arXiv)

Inverse Reinforcement Learning (IRL) seeks to infer reward functions from expert demonstrations. When demonstrations originate from multiple experts with different intentions, the problem is known as Multi-Intention IRL (MI-IRL). Recent deep generative MI-IRL approaches couple behavior clustering and reward learning, but typically require prior knowledge of the number of true behavioral modes K^*. This reliance on expert knowledge limits their adaptability to new behaviors, and only enables analysis related to the learned rewards, and not across the behavior modes used to train them. We propose Contrastive Multi-Intention IRL (CoMI-IRL), a transformer-based unsupervised framework that decouples behavior representation and clustering from downstream reward learning. Our experiments show that CoMI-IRL outperforms existing approaches without a priori knowledge of K^* or labels, while allowing for visual interpretation of behavior relationships and adaptation to unseen behavior without full retraining.