# Triple-GAIL: A Multi-Modal Imitation Learning Framework with Generative Adversarial Nets

arXiv: https://arxiv.org/abs/2005.10622 · HTML: https://mlsanity.com/paper/2005.10622/

## Key facts

- Cited by 11 papers in the map (data through 14 Oct 2026).
- Placed in Imitation learning methods, one of 13 directions in Offline RL and imitation learning from data.
- Builds on 10 of its 24 references that are in the map.
- First posted on arXiv 19 May 2020.

## Placed in

- Offline RL and imitation learning from data / [Imitation learning methods](https://mlsanity.com/offlinerl/imitation-learning-methods/)

## Builds on (most cited first, 10 of 10)

- [Trust Region Policy Optimization](https://mlsanity.com/paper/1502.05477/) (2015)
- [Generative Adversarial Imitation Learning](https://mlsanity.com/paper/1606.03476/) (2016)
- [Maximum Entropy Deep Inverse Reinforcement Learning](https://mlsanity.com/paper/1507.04888/) (2015)
- [Robust Imitation of Diverse Behaviors](https://mlsanity.com/paper/1707.02747/) (2017)
- [Learning human behaviors from motion capture by adversarial imitation](https://mlsanity.com/paper/1707.02201/) (2017)
- [Triple Generative Adversarial Nets](https://mlsanity.com/paper/1703.02291/) (2017)
- [Model-Predictive Policy Learning with Uncertainty Regularization for Driving in Dense Traffic](https://mlsanity.com/paper/1901.02705/) (2019)
- [SQIL: Imitation Learning via Reinforcement Learning with Sparse Rewards](https://mlsanity.com/paper/1905.11108/) (2019)
- [ELF: An Extensive, Lightweight and Flexible Research Platform for Real-time Strategy Games](https://mlsanity.com/paper/1707.01067/) (2017)
- [Burn-In Demonstrations for Multi-Modal Imitation Learning](https://mlsanity.com/paper/1710.05090/) (2017)

## Built on by (most cited first, 11 of 11)

- [A Survey of Deep RL and IL for Autonomous Driving Policy Learning](https://mlsanity.com/paper/2101.01993/) (2021)
- [Learning Multimodal Rewards from Rankings](https://mlsanity.com/paper/2109.12750/) (2021)
- [Adversarial Option-Aware Hierarchical Imitation Learning](https://mlsanity.com/paper/2106.05530/) (2021)
- [Diverse Imitation Learning via Self-Organizing Generative Models](https://mlsanity.com/paper/2205.03484/) (2022)
- [Hierarchical Imitation Learning for Stochastic Environments](https://mlsanity.com/paper/2309.14003/) (2023)
- [Sample Efficient Imitation Learning via Reward Function Trained in Advance](https://mlsanity.com/paper/2111.11711/) (2021)
- [PAIL: Performance based Adversarial Imitation Learning Engine for Carbon Neutral Optimization](https://mlsanity.com/paper/2407.08910/) (2024)
- [Learning Strategy Representation for Imitation Learning in Multi-Agent Games](https://mlsanity.com/paper/2409.19363/) (2024)
- [A New Approach to Training Multiple Cooperative Agents for Autonomous Driving](https://mlsanity.com/paper/2209.02157/) (2022)
- [MRIC: Model-Based Reinforcement-Imitation Learning with Mixture-of-Codebooks for Autonomous Driving Simulation](https://mlsanity.com/paper/2404.18464/) (2024)
- [Imitation Learning in the Deep Learning Era: A Novel Taxonomy and Recent Advances](https://mlsanity.com/paper/2511.03565/) (2025)

## Abstract (arXiv)

Generative adversarial imitation learning (GAIL) has shown promising results by taking advantage of generative adversarial nets, especially in the field of robot learning. However, the requirement of isolated single modal demonstrations limits the scalability of the approach to real world scenarios such as autonomous vehicles' demand for a proper understanding of human drivers' behavior. In this paper, we propose a novel multi-modal GAIL framework, named Triple-GAIL, that is able to learn skill selection and imitation jointly from both expert demonstrations and continuously generated experiences with data augmentation purpose by introducing an auxiliary skill selector. We provide theoretical guarantees on the convergence to optima for both of the generator and the selector respectively. Experiments on real driver trajectories and real-time strategy game datasets demonstrate that Triple-GAIL can better fit multi-modal behaviors close to the demonstrators and outperforms state-of-the-art methods.