# Real-World Reinforcement Learning of Active Perception Behaviors

arXiv: https://arxiv.org/abs/2512.01188 · HTML: https://mlsanity.com/paper/2512.01188/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Placed in RL for robot locomotion and manipulation, one of 15 directions in Deep reinforcement learning methods.
- Builds on 37 of its 61 references that are in the map.
- First posted on arXiv 1 Dec 2025.

## Placed in

- Deep reinforcement learning methods / [RL for robot locomotion and manipulation](https://mlsanity.com/deeprl/rl-for-robot-locomotion-and-manipulation/)

## Builds on (most cited first, 30 of 37)

- [DINOv2: Learning Robust Visual Features without Supervision](https://mlsanity.com/paper/2304.07193/) (2023)
- [π0.5: a Vision-Language-Action Model with Open-World Generalization](https://mlsanity.com/paper/2504.16054/) (2025)
- [Offline Reinforcement Learning with Implicit Q-Learning](https://mlsanity.com/paper/2110.06169/) (2021)
- [DROID: A Large-Scale In-The-Wild Robot Manipulation Dataset](https://mlsanity.com/paper/2403.12945/) (2024)
- [Advantage-Weighted Regression: Simple and Scalable Off-Policy Reinforcement Learning](https://mlsanity.com/paper/1910.00177/) (2019)
- [AWAC: Accelerating Online Reinforcement Learning with Offline Datasets](https://mlsanity.com/paper/2006.09359/) (2020)
- [Learning Quadrupedal Locomotion over Challenging Terrain](https://mlsanity.com/paper/2010.11251/) (2020)
- [RMA: Rapid Motor Adaptation for Legged Robots](https://mlsanity.com/paper/2107.04034/) (2021)
- [Efficient Online Reinforcement Learning with Offline Data](https://mlsanity.com/paper/2302.02948/) (2023)
- [Critic Regularized Regression](https://mlsanity.com/paper/2006.15134/) (2020)
- [Asymmetric Actor Critic for Image-Based Robot Learning](https://mlsanity.com/paper/1710.06542/) (2017)
- [OGBench: Benchmarking Offline Goal-Conditioned RL](https://mlsanity.com/paper/2410.20092/) (2024)
- [Cal-QL: Calibrated Offline RL Pre-Training for Efficient Online Fine-Tuning](https://mlsanity.com/paper/2303.05479/) (2023)
- [Hi Robot: Open-Ended Instruction Following with Hierarchical Vision-Language-Action Models](https://mlsanity.com/paper/2502.19417/) (2025)
- [Offline-to-Online Reinforcement Learning via Balanced Replay and Pessimistic Q-Ensemble](https://mlsanity.com/paper/2107.00591/) (2021)
- [Distilling Policy Distillation](https://mlsanity.com/paper/1902.02186/) (2019)
- [Interactive Perception: Leveraging Action in Perception and Perception in Action](https://mlsanity.com/paper/1604.03670/) (2016)
- [FisherRF: Active View Selection and Uncertainty Quantification for Radiance Fields using Fisher Information](https://mlsanity.com/paper/2311.17874/) (2023)
- [Reinforcement Learning, Bit by Bit](https://mlsanity.com/paper/2103.04047/) (2021)
- [Suphx: Mastering Mahjong with Deep Reinforcement Learning](https://mlsanity.com/paper/2003.13590/) (2020)
- [Sequential Dexterity: Chaining Dexterous Policies for Long-Horizon Manipulation](https://mlsanity.com/paper/2309.00987/) (2023)
- [Vision-Based Manipulators Need to Also See from Their Hands](https://mlsanity.com/paper/2203.12677/) (2022)
- [Simple Agent, Complex Environment: Efficient Reinforcement Learning with Agent States](https://mlsanity.com/paper/2102.05261/) (2021)
- [Finetuning Offline World Models in the Real World](https://mlsanity.com/paper/2310.16029/) (2023)
- [Vision in Action: Learning Active Perception from Human Demonstrations](https://mlsanity.com/paper/2506.15666/) (2025)
- [Reinforcement Learning of Active Vision for Manipulating Objects under Occlusions](https://mlsanity.com/paper/1811.08067/) (2018)
- [Active Vision Might Be All You Need: Exploring Active Vision in Bimanual Robotic Manipulation](https://mlsanity.com/paper/2409.17435/) (2024)
- [On Value Functions and the Agent-Environment Boundary](https://mlsanity.com/paper/1905.13341/) (2019)
- [Privileged Sensing Scaffolds Reinforcement Learning](https://mlsanity.com/paper/2405.14853/) (2024)
- [Object Finding in Cluttered Scenes Using Interactive Perception](https://mlsanity.com/paper/1911.07482/) (2019)

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

- [Reinformed Dreamer: An Asymmetric World Model Efficiently Trained through Latent Guidance](https://mlsanity.com/paper/2607.26040/) (2026)

## Abstract (arXiv)

A robot's instantaneous sensory observations do not always reveal task-relevant state information. Under such partial observability, optimal behavior typically involves explicitly acting to gain the missing information. Today's standard robot learning techniques struggle to produce such active perception behaviors. We propose a simple real-world robot learning recipe to efficiently train active perception policies. Our approach, asymmetric advantage weighted regression (AAWR), exploits access to "privileged" extra sensors at training time. The privileged sensors enable training high-quality privileged value functions that aid in estimating the advantage of the target policy. Bootstrapping from a small number of potentially suboptimal demonstrations and an easy-to-obtain coarse policy initialization, AAWR quickly acquires active perception behaviors and boosts task performance. In evaluations on 8 manipulation tasks on 3 robots spanning varying degrees of partial observability, AAWR synthesizes reliable active perception behaviors that outperform all prior approaches. When initialized with a "generalist" robot policy that struggles with active perception tasks, AAWR efficiently generates information-gathering behaviors that allow it to operate under severe partial observability for manipulation tasks. Website: https://penn-pal-lab.github.io/aawr/