# Neural Policy Style Transfer

arXiv: https://arxiv.org/abs/2402.00677 · HTML: https://mlsanity.com/paper/2402.00677/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Placed in Deep RL algorithms and representations, one of 15 directions in Deep reinforcement learning methods.
- Builds on 9 of its 26 references that are in the map.
- First posted on arXiv 1 Feb 2024.

## Placed in

- Deep reinforcement learning methods / [Deep RL algorithms and representations](https://mlsanity.com/deeprl/deep-rl-algorithms-and-representations/)

## Builds on (most cited first, 9 of 9)

- [Adam: A Method for Stochastic Optimization](https://mlsanity.com/paper/1412.6980/) (2014)
- [Very Deep Convolutional Networks for Large-Scale Image Recognition](https://mlsanity.com/paper/1409.1556/) (2014)
- [Playing Atari with Deep Reinforcement Learning](https://mlsanity.com/paper/1312.5602/) (2013)
- [A Brief Survey of Deep Reinforcement Learning](https://mlsanity.com/paper/1708.05866/) (2017)
- [A Learned Representation For Artistic Style](https://mlsanity.com/paper/1610.07629/) (2016)
- [Style Transfer in Text: Exploration and Evaluation](https://mlsanity.com/paper/1711.06861/) (2017)
- [Deep Painterly Harmonization](https://mlsanity.com/paper/1804.03189/) (2018)
- [Automatic Semantic Style Transfer using Deep Convolutional Neural Networks and Soft Masks](https://mlsanity.com/paper/1708.09641/) (2017)
- [Robot Imitation through Vision, Kinesthetic and Force Features with Online Adaptation to Changing Environments](https://mlsanity.com/paper/1807.09177/) (2018)

## Built on by (most cited first, 1 of 1)

- [End-to-end example-based sim-to-real RL policy transfer based on neural stylisation with application to robotic cutting](https://mlsanity.com/paper/2601.20846/) (2026)

## Abstract (arXiv)

Style Transfer has been proposed in a number of fields: fine arts, natural language processing, and fixed trajectories. We scale this concept up to control policies within a Deep Reinforcement Learning infrastructure. Each network is trained to maximize the expected reward, which typically encodes the goal of an action, and can be described as the content. The expressive power of deep neural networks enables encoding a secondary task, which can be described as the style. The Neural Policy Style Transfer (NPST) algorithm is proposed to transfer the style of one policy to another, while maintaining the content of the latter. Different policies are defined via Deep Q-Network architectures. These models are trained using demonstrations through Inverse Reinforcement Learning. Two different sets of user demonstrations are performed, one for content and other for style. Different styles are encoded as defined by user demonstrations. The generated policy is the result of feeding a content policy and a style policy to the NPST algorithm. Experiments are performed in a catch-ball game inspired by the Deep Reinforcement Learning classical Atari games; and a real-world painting scenario with a full-sized humanoid robot, based on previous works of the authors. The implementation of three different Q-Network architectures (Shallow, Deep and Deep Recurrent Q-Network) to encode the policies within the NPST framework is proposed and the results obtained in the experiments with each of these architectures compared.