# Reinforcement Learning of Active Vision for Manipulating Objects under Occlusions

arXiv: https://arxiv.org/abs/1811.08067 · HTML: https://mlsanity.com/paper/1811.08067/

## Key facts

- Cited by 25 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 20 Nov 2018.

## Built on by (most cited first, 25 of 25)

- [Memory-based Deep Reinforcement Learning for POMDPs](https://mlsanity.com/paper/2102.12344/) (2021)
- [Look Closer: Bridging Egocentric and Third-Person Views with Transformers for Robotic Manipulation](https://mlsanity.com/paper/2201.07779/) (2022)
- [Visual Reinforcement Learning with Self-Supervised 3D Representations](https://mlsanity.com/paper/2210.07241/) (2022)
- [Frame Mining: a Free Lunch for Learning Robotic Manipulation from 3D Point Clouds](https://mlsanity.com/paper/2210.07442/) (2022)
- [Play it by Ear: Learning Skills amidst Occlusion through Audio-Visual Imitation Learning](https://mlsanity.com/paper/2205.14850/) (2022)
- [A Universal Semantic-Geometric Representation for Robotic Manipulation](https://mlsanity.com/paper/2306.10474/) (2023)
- [BFA: Best-Feature-Aware Fusion for Multi-View Fine-grained Manipulation](https://mlsanity.com/paper/2502.11161/) (2025)
- [Goal-Aware Cross-Entropy for Multi-Target Reinforcement Learning](https://mlsanity.com/paper/2110.12985/) (2021)
- [Grasp, See, and Place: Efficient Unknown Object Rearrangement with Policy Structure Prior](https://mlsanity.com/paper/2402.15402/) (2024)
- [Observe Then Act: Asynchronous Active Vision-Action Model for Robotic Manipulation](https://mlsanity.com/paper/2409.14891/) (2024)
- [3D Equivariant Visuomotor Policy Learning via Spherical Projection](https://mlsanity.com/paper/2505.16969/) (2025)
- [Distribution Guided Active Feature Acquisition](https://mlsanity.com/paper/2410.03915/) (2024)
- [Learning to Look: Seeking Information for Decision Making via Policy Factorization](https://mlsanity.com/paper/2410.18964/) (2024)
- [Active Safety Envelopes using Light Curtains with Probabilistic Guarantees](https://mlsanity.com/paper/2107.04000/) (2021)
- [The Introspective Agent: Interdependence of Strategy, Physiology, and Sensing for Embodied Agents](https://mlsanity.com/paper/2201.00411/) (2022)
- [L-SA: Learning Under-Explored Targets in Multi-Target Reinforcement Learning](https://mlsanity.com/paper/2305.13741/) (2023)
- [Towards Cost Sensitive Decision Making](https://mlsanity.com/paper/2410.03892/) (2024)
- [Apple: Toward General Active Perception via Reinforcement Learning](https://mlsanity.com/paper/2505.06182/) (2025)
- [Environment-aware Interactive Movement Primitives for Object Reaching in Clutter](https://mlsanity.com/paper/2210.16194/) (2022)
- [SENSOR: Imitate Third-Person Expert's Behaviors via Active Sensoring](https://mlsanity.com/paper/2404.03386/) (2024)
- [Real-World Reinforcement Learning of Active Perception Behaviors](https://mlsanity.com/paper/2512.01188/) (2025)
- [Active Velocity Estimation using Light Curtains via Self-Supervised Multi-Armed Bandits](https://mlsanity.com/paper/2302.12597/) (2023)
- [Active Vision Reinforcement Learning under Limited Visual Observability](https://mlsanity.com/paper/2306.00975/) (2023)
- [GoStop: Reinforcement Learning for Adaptive Temporal Aggregation in Event-Based Feature Tracking](https://mlsanity.com/paper/2607.15699/) (2026)
- [LEAP: Learning Emergent Active Perception for Quadruped Navigation](https://mlsanity.com/paper/2609.17628/) (2026)

## Abstract (arXiv)

We consider artificial agents that learn to jointly control their gripperand camera in order to reinforcement learn manipulation policies in the presenceof occlusions from distractor objects. Distractors often occlude the object of in-terest and cause it to disappear from the field of view. We propose hand/eye con-trollers that learn to move the camera to keep the object within the field of viewand visible, in coordination to manipulating it to achieve the desired goal, e.g.,pushing it to a target location. We incorporate structural biases of object-centricattention within our actor-critic architectures, which our experiments suggest tobe a key for good performance. Our results further highlight the importance ofcurriculum with regards to environment difficulty. The resulting active vision /manipulation policies outperform static camera setups for a variety of clutteredenvironments.