Research map / Multi-agent systems and games / Human-AI and goal-conditioned
Collaborative Deep Reinforcement Learning for Joint Object Search
Check your idea against 108,967 papers
AI-extracted summary. Written by AI from the paper's title only (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Measured effects reported in the paper
| What was changed | Where | Measured | Effect |
|---|---|---|---|
| Add collaborative joint search | Single-agent active localization · D1: person+bicycle (VOC) | localization accuracy: 76.9 -> 86.0; 61.5 -> 77.8 | Helped |
| Add collaborative joint search | Single-agent active localization · D1: ball+racket (COCO) | localization accuracy: 52.0 -> 53.9; 59.3 -> 60.2 | Helped |
| Add collaborative joint search | Single-agent active localization · D1: person+handbag (COCO) | localization accuracy: 80.4 -> 82.5; 45.1 -> 46.4 | Helped |
| Add collaborative joint search | Single-agent active localization · D1: laptop+keyboard (COCO) | localization accuracy: 60.6 -> 64.6; 56.9 -> 64.7 | Helped |
| Add collaborative joint search | Ours (Single) · D2: person (VOC) | localization accuracy: 44.6 -> 45.6 | Helped |
| Add collaborative joint search | Ours (Single) · D2: bicycle (VOC) | localization accuracy: 62.2 -> 63.9 | Helped |
| Add collaborative joint search | Single-agent active localization · COCO: fork+knife | localization accuracy: 31.9 -> 34.7; 45.2 -> 46.9 | Helped |
| Add collaborative joint search | Single-agent active localization · COCO: oven+sink | localization accuracy: 38.2 -> 42.4; 34.3 -> 37.7 | Helped |
| Add collaborative joint search | Single-agent active localization · COCO: chair+tv | localization accuracy: 35.1 -> 35.9; 57.1 -> 56.2 | Mixed |
| Add collaborative joint search | Single-agent active localization · ImageNet: guitar+mike | localization accuracy: 80.9 -> 87.7; 45.4 -> 50.2 | Helped |
Closest papers by meaning
- Cooperative Exploration for Multi-Agent Deep Reinforcement Learning (ICML 2021 · similarity 0.85)
- Learning Transferable Reward for Query Object Localization with Policy Adaptation (ICLR 2022 · similarity 0.85)
- Enhancing Cooperative Multi-Agent Reinforcement Learning with State Modelling and Adversarial Exploration (ICML 2025 · similarity 0.85)
- MAT-Agent: Adaptive Multi-Agent Training Optimization (NeurIPS 2025 · similarity 0.84)
- Focus-Then-Decide: Segmentation-Assisted Reinforcement Learning (AAAI 2024 · similarity 0.83)
- Inverse Factorized Soft Q-Learning for Cooperative Multi-agent Imitation Learning (NeurIPS 2024 · similarity 0.83)
Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.