Pre-Trained Image Encoder for Generalizable Visual Reinforcement Learning

Authors: Zhecheng Yuan, Zhengrong Xue, Bo Yuan, Xueqian Wang, YI WU, Yang Gao, Huazhe Xu

NeurIPS 2022 | Conference PDF | Archive PDF | Plain Text | LLM Run Details

Reproducibility Variable Result LLM Response
Research Type Experimental Extensive experiments are conducted on DMControl Generalization Benchmark, DMControl Manipulation Tasks, Drawer World, and CARLA to verify the effectiveness of PIE-G.
Researcher Affiliation Academia Zhecheng Yuan1, Zhengrong Xue2, Bo Yuan3, Xueqian Wang1, Yi Wu1,4, Yang Gao1,4, Huazhe Xu1,4 1 Tsinghua University 2 Shanghai Jiao Tong University 3 Qianyuan Institute of Sciences 4 Shanghai Qi Zhi Institute
Pseudocode No The paper does not contain any clearly labeled pseudocode or algorithm blocks.
Open Source Code Yes Project Page: https://sites.google.com/view/pie-g/home. and Did you include the code, data, and instructions needed to reproduce the main experimental results (either in the supplemental material or as a URL)? [Yes] In the supplementary material
Open Datasets Yes DMControl Generalization Benchmark (DMC-GB) [26], DMControl Manipulation Tasks [72], Drawer World [75] that is modified from Meta World [82], and CARLA [13], a realistic autonomous driving simulator. and Image Net pre-trained Res Net model
Dataset Splits No The paper describes training and evaluation procedures on benchmarks but does not provide explicit training, validation, or test dataset splits (e.g., 80/10/10 percentages or specific sample counts) for reproducibility of data partitioning.
Hardware Specification Yes Did you include the total amount of compute and the type of resources used (e.g., type of GPUs, internal cluster, or cloud provider)? [Yes] In the supplementary material
Software Dependencies No The paper states that training details are in the supplementary material, but it does not explicitly provide specific software dependencies with version numbers in the main text.
Experiment Setup Yes More training details and environment descriptions are in Appendix B. and Did you specify all the training details (e.g., data splits, hyperparameters, how they were chosen)? [Yes] In the supplementary material