Focus-Then-Decide: Segmentation-Assisted Reinforcement Learning
Authors: Chao Chen, Jiacheng Xu, Weijian Liao, Hao Ding, Zongzhang Zhang, Yang Yu, Rui Zhao
AAAI 2024 | Conference PDF | Archive PDF | Plain Text | LLM Run Details
| Reproducibility Variable | Result | LLM Response |
|---|---|---|
| Research Type | Experimental | Experimental results on challenging tasks based on Deep Mind Control Suite and Franka Emika Robotics demonstrate that our method can quickly and accurately pinpoint objects of interest in noisy environments. |
| Researcher Affiliation | Collaboration | 1 National Key Laboratory for Novel Software Technology, Nanjing University, China 2 School of Artificial Intelligence, Nanjing University, China 3 Tencent Robotics X, Shenzhen, China |
| Pseudocode | No | The paper provides architectural diagrams and equations, but it does not include any clearly labeled pseudocode or algorithm blocks. |
| Open Source Code | Yes | Code: https://github.com/LAMDA-RL/FTD |
| Open Datasets | Yes | We choose Deep Mind Control (DMC) Suite, a widely used benchmark... Franka Emika Robotics (Yuan et al. 2023) as our second experiment environment... a larger video dataset is played as background in RGB mode (Hansen, Su, and Wang 2021). |
| Dataset Splits | No | Specifically, 80 color video clips will loop on the background during training, and 20 clips for testing. The paper does not explicitly state validation splits for the main experimental environments or the background video clips. |
| Hardware Specification | No | The paper does not provide specific details about the hardware (e.g., GPU/CPU models, memory) used to run the experiments. |
| Software Dependencies | No | The paper mentions using Soft Actor-Critic (SAC) and Mobile SAM as foundational models, but it does not provide specific version numbers for these or any other software dependencies, programming languages, or libraries used in the experiments. |
| Experiment Setup | Yes | where all ηi are hyper-parameters and set to 1 by default. For details in the experiment, please refer to the appendix1. 1https://www.lamda.nju.edu.cn/chenc/AAAI24-Appendix.pdf |