# Latent Policies for Adversarial Imitation Learning

arXiv: https://arxiv.org/abs/2206.11299 · HTML: https://mlsanity.com/paper/2206.11299/

## Key facts

- Cited by 3 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 30 of its 48 references that are in the map.
- First posted on arXiv 22 Jun 2022.

## Placed in

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

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

- [Adam: A Method for Stochastic Optimization](https://mlsanity.com/paper/1412.6980/) (2014)
- [Generative Adversarial Networks](https://mlsanity.com/paper/2203.00667/) (2022)
- [Soft Actor-Critic: Off-Policy Maximum Entropy Deep Reinforcement Learning with a Stochastic Actor](https://mlsanity.com/paper/1801.01290/) (2018)
- [Improved Training of Wasserstein GANs](https://mlsanity.com/paper/1704.00028/) (2017)
- [OpenAI Gym](https://mlsanity.com/paper/1606.01540/) (2016)
- [Spectral Normalization for Generative Adversarial Networks](https://mlsanity.com/paper/1802.05957/) (2018)
- [Generative Adversarial Imitation Learning](https://mlsanity.com/paper/1606.03476/) (2016)
- [Learning Latent Dynamics for Planning from Pixels](https://mlsanity.com/paper/1811.04551/) (2018)
- [Off-Policy Deep Reinforcement Learning without Exploration](https://mlsanity.com/paper/1812.02900/) (2018)
- [robosuite: A Modular Simulation Framework and Benchmark for Robot Learning](https://mlsanity.com/paper/2009.12293/) (2020)
- [Learning Robust Rewards with Adversarial Inverse Reinforcement Learning](https://mlsanity.com/paper/1710.11248/) (2017)
- [Inverse Reward Design](https://mlsanity.com/paper/1711.02827/) (2017)
- [Stochastic Latent Actor-Critic: Deep Reinforcement Learning with a Latent Variable Model](https://mlsanity.com/paper/1907.00953/) (2019)
- [Discriminator-Actor-Critic: Addressing Sample Inefficiency and Reward Bias in Adversarial Imitation Learning](https://mlsanity.com/paper/1809.02925/) (2018)
- [A Divergence Minimization Perspective on Imitation Learning Methods](https://mlsanity.com/paper/1911.02256/) (2019)
- [A Connection between Generative Adversarial Networks, Inverse Reinforcement Learning, and Energy-Based Models](https://mlsanity.com/paper/1611.03852/) (2016)
- [PLAS: Latent Action Space for Offline Reinforcement Learning](https://mlsanity.com/paper/2011.07213/) (2020)
- [Reinforcement and Imitation Learning for Diverse Visuomotor Skills](https://mlsanity.com/paper/1802.09564/) (2018)
- [Gradient Estimation Using Stochastic Computation Graphs](https://mlsanity.com/paper/1506.05254/) (2015)
- [Variational Discriminator Bottleneck: Improving Imitation Learning, Inverse RL, and GANs by Constraining Information Flow](https://mlsanity.com/paper/1810.00821/) (2018)
- [Imitating Latent Policies from Observation](https://mlsanity.com/paper/1805.07914/) (2018)
- [Robust Imitation of Diverse Behaviors](https://mlsanity.com/paper/1707.02747/) (2017)
- [What Matters for Adversarial Imitation Learning?](https://mlsanity.com/paper/2106.00672/) (2021)
- [Plannable Approximations to MDP Homomorphisms: Equivariance under Actions](https://mlsanity.com/paper/2002.11963/) (2020)
- [Task-Relevant Adversarial Imitation Learning](https://mlsanity.com/paper/1910.01077/) (2019)
- [Visual Adversarial Imitation Learning using Variational Models](https://mlsanity.com/paper/2107.08829/) (2021)
- [Sample-Efficient Imitation Learning via Generative Adversarial Nets](https://mlsanity.com/paper/1809.02064/) (2018)
- [LASER: Learning a Latent Action Space for Efficient Reinforcement Learning](https://mlsanity.com/paper/2103.15793/) (2021)
- [Learning Belief Representations for Imitation Learning in POMDPs](https://mlsanity.com/paper/1906.09510/) (2019)
- [Prediction and Control with Temporal Segment Models](https://mlsanity.com/paper/1703.04070/) (2017)

## Built on by (most cited first, 3 of 3)

- [Deep Generative Models for Offline Policy Learning: Tutorial, Survey, and Perspectives on Future Directions](https://mlsanity.com/paper/2402.13777/) (2024)
- [CEIL: Generalized Contextual Imitation Learning](https://mlsanity.com/paper/2306.14534/) (2023)
- [Sample-efficient Adversarial Imitation Learning](https://mlsanity.com/paper/2303.07846/) (2023)

## Abstract (arXiv)

This paper considers learning robot locomotion and manipulation tasks from expert demonstrations. Generative adversarial imitation learning (GAIL) trains a discriminator that distinguishes expert from agent transitions, and in turn use a reward defined by the discriminator output to optimize a policy generator for the agent. This generative adversarial training approach is very powerful but depends on a delicate balance between the discriminator and the generator training. In high-dimensional problems, the discriminator training may easily overfit or exploit associations with task-irrelevant features for transition classification. A key insight of this work is that performing imitation learning in a suitable latent task space makes the training process stable, even in challenging high-dimensional problems. We use an action encoder-decoder model to obtain a low-dimensional latent action space and train a LAtent Policy using Adversarial imitation Learning (LAPAL). The encoder-decoder model can be trained offline from state-action pairs to obtain a task-agnostic latent action representation or online, simultaneously with the discriminator and generator training, to obtain a task-aware latent action representation. We demonstrate that LAPAL training is stable, with near-monotonic performance improvement, and achieves expert performance in most locomotion and manipulation tasks, while a GAIL baseline converges slower and does not achieve expert performance in high-dimensional environments.