# Inverse Reinforcement Learning via Deep Gaussian Process

arXiv: https://arxiv.org/abs/1512.08065 · HTML: https://mlsanity.com/paper/1512.08065/

## Key facts

- Cited by 6 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 26 Dec 2015.

## Built on by (most cited first, 6 of 6)

- [Robust and Adaptive Temporal-Difference Learning Using An Ensemble of Gaussian Processes](https://mlsanity.com/paper/2112.00882/) (2021)
- [Basis for Intentions: Efficient Inverse Reinforcement Learning using Past Experience](https://mlsanity.com/paper/2208.04919/) (2022)
- [Bayesian Inverse Reinforcement Learning for Collective Animal Movement](https://mlsanity.com/paper/2009.04003/) (2020)
- [Towards Inverse Reinforcement Learning for Limit Order Book Dynamics](https://mlsanity.com/paper/1906.04813/) (2019)
- [Weighted Maximum Entropy Inverse Reinforcement Learning](https://mlsanity.com/paper/2208.09611/) (2022)
- [Deep Q-Exponential Processes](https://mlsanity.com/paper/2410.22119/) (2024)

## Abstract (arXiv)

We propose a new approach to inverse reinforcement learning (IRL) based on the deep Gaussian process (deep GP) model, which is capable of learning complicated reward structures with few demonstrations. Our model stacks multiple latent GP layers to learn abstract representations of the state feature space, which is linked to the demonstrations through the Maximum Entropy learning framework. Incorporating the IRL engine into the nonlinear latent structure renders existing deep GP inference approaches intractable. To tackle this, we develop a non-standard variational approximation framework which extends previous inference schemes. This allows for approximate Bayesian treatment of the feature space and guards against overfitting. Carrying out representation and inverse reinforcement learning simultaneously within our model outperforms state-of-the-art approaches, as we demonstrate with experiments on standard benchmarks ("object world","highway driving") and a new benchmark ("binary world").