# POAR: Efficient Policy Optimization via Online Abstract State Representation Learning

arXiv: https://arxiv.org/abs/2109.08642 · HTML: https://mlsanity.com/paper/2109.08642/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 19 of its 44 references that are in the map.
- First posted on arXiv 17 Sep 2021.

## Builds on (most cited first, 19 of 19)

- [Adam: A Method for Stochastic Optimization](https://mlsanity.com/paper/1412.6980/) (2014)
- [Proximal Policy Optimization Algorithms](https://mlsanity.com/paper/1707.06347/) (2017)
- [A Simple Framework for Contrastive Learning of Visual Representations](https://mlsanity.com/paper/2002.05709/) (2020)
- [Momentum Contrast for Unsupervised Visual Representation Learning](https://mlsanity.com/paper/1911.05722/) (2019)
- [Bootstrap your own latent: A new approach to self-supervised Learning](https://mlsanity.com/paper/2006.07733/) (2020)
- [Learning deep representations by mutual information estimation and maximization](https://mlsanity.com/paper/1808.06670/) (2018)
- [Learning Representations by Maximizing Mutual Information Across Views](https://mlsanity.com/paper/1906.00910/) (2019)
- [Model-Based Reinforcement Learning for Atari](https://mlsanity.com/paper/1903.00374/) (2019)
- [Guided Cost Learning: Deep Inverse Optimal Control via Policy Optimization](https://mlsanity.com/paper/1603.00448/) (2016)
- [Data-Efficient Reinforcement Learning with Self-Predictive Representations](https://mlsanity.com/paper/2007.05929/) (2020)
- [Imitation from Observation: Learning to Imitate Behaviors from Raw Video via Context Translation](https://mlsanity.com/paper/1707.03374/) (2017)
- [One-Shot Imitation from Observing Humans via Domain-Adaptive Meta-Learning](https://mlsanity.com/paper/1802.01557/) (2018)
- [State Representation Learning for Control: An Overview](https://mlsanity.com/paper/1802.04181/) (2018)
- [One Policy to Control Them All: Shared Modular Policies for Agent-Agnostic Control](https://mlsanity.com/paper/2007.04976/) (2020)
- [XIRL: Cross-embodiment Inverse Reinforcement Learning](https://mlsanity.com/paper/2106.03911/) (2021)
- [Pretraining Representations for Data-Efficient Reinforcement Learning](https://mlsanity.com/paper/2106.04799/) (2021)
- [Bootstrap Latent-Predictive Representations for Multitask Reinforcement Learning](https://mlsanity.com/paper/2004.14646/) (2020)
- [Variable Impedance Control in End-Effector Space: An Action Space for Reinforcement Learning in Contact-Rich Tasks](https://mlsanity.com/paper/1906.08880/) (2019)
- [Decoupling feature extraction from policy learning: assessing benefits of state representation learning in goal based robotics](https://mlsanity.com/paper/1901.08651/) (2019)

## Abstract (arXiv)

While the rapid progress of deep learning fuels end-to-end reinforcement learning (RL), direct application, especially in high-dimensional space like robotic scenarios still suffers from low sample efficiency. Therefore State Representation Learning (SRL) is proposed to specifically learn to encode task-relevant features from complex sensory data into low-dimensional states. However, the pervasive implementation of SRL is usually conducted by a decoupling strategy in which the observation-state mapping is learned separately, which is prone to over-fit. To handle such problem, we summarize the state-of-the-art (SOTA) SRL sub-tasks in previous works and present a new algorithm called Policy Optimization via Abstract Representation which integrates SRL into the policy optimization phase. Firstly, We engage RL loss to assist in updating SRL model so that the states can evolve to meet the demand of RL and maintain a good physical interpretation. Secondly, we introduce a dynamic loss weighting mechanism so that both models can efficiently adapt to each other. Thirdly, we introduce a new SRL prior called domain resemblance to leverage expert demonstration to improve SRL interpretations. Finally, we provide a real-time access of state graph to monitor the course of learning. Experiments indicate that POAR significantly outperforms SOTA RL algorithms and decoupling SRL strategies in terms of sample efficiency and final rewards. We empirically verify POAR to efficiently handle tasks in high dimensions and facilitate training real-life robots directly from scratch.