# Collaborative Deep Reinforcement Learning for Joint Object Search

arXiv: https://arxiv.org/abs/1702.05573 · HTML: https://mlsanity.com/paper/1702.05573/

## Key facts

- Cited by 9 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 18 Feb 2017.

## Built on by (most cited first, 9 of 9)

- [Optimal Boxes: Boosting End-to-End Scene Text Recognition by Adjusting Annotated Bounding Boxes via Reinforcement Learning](https://mlsanity.com/paper/2207.11934/) (2022)
- [Towards More Human-like AI Communication: A Review of Emergent Communication Research](https://mlsanity.com/paper/2308.02541/) (2023)
- [AdaZoom: Adaptive Zoom Network for Multi-Scale Object Detection in Large Scenes](https://mlsanity.com/paper/2106.10409/) (2021)
- [Recent Advances in Embedding Methods for Multi-Object Tracking: A Survey](https://mlsanity.com/paper/2205.10766/) (2022)
- [Semantic-Aware Collaborative Deep Reinforcement Learning Over Wireless Cellular Networks](https://mlsanity.com/paper/2111.12064/) (2021)
- [Collaborative Multi-Agent Video Fast-Forwarding](https://mlsanity.com/paper/2305.17569/) (2023)
- [Dynamic Multi-Scale Loss Optimization for Object Detection](https://mlsanity.com/paper/2108.04014/) (2021)
- [Belief States for Cooperative Multi-Agent Reinforcement Learning under Partial Observability](https://mlsanity.com/paper/2504.08417/) (2025)
- [Weakly Supervised Scene Text Detection using Deep Reinforcement Learning](https://mlsanity.com/paper/2201.04866/) (2022)

## Abstract (arXiv)

We examine the problem of joint top-down active search of multiple objects under interaction, e.g., person riding a bicycle, cups held by the table, etc.. Such objects under interaction often can provide contextual cues to each other to facilitate more efficient search. By treating each detector as an agent, we present the first collaborative multi-agent deep reinforcement learning algorithm to learn the optimal policy for joint active object localization, which effectively exploits such beneficial contextual information. We learn inter-agent communication through cross connections with gates between the Q-networks, which is facilitated by a novel multi-agent deep Q-learning algorithm with joint exploitation sampling. We verify our proposed method on multiple object detection benchmarks. Not only does our model help to improve the performance of state-of-the-art active localization models, it also reveals interesting co-detection patterns that are intuitively interpretable.