# PEARL: Parallelized Expert-Assisted Reinforcement Learning for Scene Rearrangement Planning

arXiv: https://arxiv.org/abs/2105.04088 · HTML: https://mlsanity.com/paper/2105.04088/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 14 of its 37 references that are in the map.
- First posted on arXiv 10 May 2021.

## Builds on (most cited first, 14 of 14)

- [Asynchronous Methods for Deep Reinforcement Learning](https://mlsanity.com/paper/1602.01783/) (2016)
- [Prioritized Experience Replay](https://mlsanity.com/paper/1511.05952/) (2015)
- [Semantic Scene Completion from a Single Depth Image](https://mlsanity.com/paper/1611.08974/) (2016)
- [3D-FRONT: 3D Furnished Rooms with layOuts and semaNTics](https://mlsanity.com/paper/2011.09127/) (2020)
- [Reinforced Cross-Modal Matching and Self-Supervised Imitation Learning for Vision-Language Navigation](https://mlsanity.com/paper/1811.10092/) (2018)
- [Thinking Fast and Slow with Deep Learning and Tree Search](https://mlsanity.com/paper/1705.08439/) (2017)
- [Rearrangement: A Challenge for Embodied AI](https://mlsanity.com/paper/2011.01975/) (2020)
- [Fast and Flexible Indoor Scene Synthesis via Deep Convolutional Generative Models](https://mlsanity.com/paper/1811.12463/) (2018)
- [Deep Generative Modeling for Scene Synthesis via Hybrid Representations](https://mlsanity.com/paper/1808.02084/) (2018)
- [Monte-Carlo Tree Search for Efficient Visually Guided Rearrangement Planning](https://mlsanity.com/paper/1904.10348/) (2019)
- [Dual Policy Iteration](https://mlsanity.com/paper/1805.10755/) (2018)
- [Automatic Generation of Constrained Furniture Layouts](https://mlsanity.com/paper/1711.10939/) (2017)
- [Learning Manipulation States and Actions for Efficient Non-prehensile Rearrangement Planning](https://mlsanity.com/paper/1901.03557/) (2019)
- [Object Rearrangement with Nested Nonprehensile Manipulation Actions](https://mlsanity.com/paper/1905.07505/) (2019)

## Abstract (arXiv)

Scene Rearrangement Planning (SRP) is an interior task proposed recently. The previous work defines the action space of this task with handcrafted coarse-grained actions that are inflexible to be used for transforming scene arrangement and intractable to be deployed in practice. Additionally, this new task lacks realistic indoor scene rearrangement data to feed popular data-hungry learning approaches and meet the needs of quantitative evaluation. To address these problems, we propose a fine-grained action definition for SRP and introduce a large-scale scene rearrangement dataset. We also propose a novel learning paradigm to efficiently train an agent through self-playing, without any prior knowledge. The agent trained via our paradigm achieves superior performance on the introduced dataset compared to the baseline agents. We provide a detailed analysis of the design of our approach in our experiments.