Cross-Domain Policy Adaptation by Capturing Representation Mismatch

Authors: Jiafei Lyu, Chenjia Bai, Jing-Wen Yang, Zongqing Lu, Xiu Li

ICML 2024 | Conference PDF | Archive PDF | Plain Text | LLM Run Details

Reproducibility Variable Result LLM Response
Research Type Experimental We conduct extensive experiments on environments with kinematic and morphology mismatch, and the results show that our method exhibits strong performance on many tasks.
Researcher Affiliation Collaboration 1Tsinghua Shenzhen International Graduate School, Tsinghua University 2Shanghai Artificial Intelligence Laboratory 3Tencent IEG 4School of Computer Science, Peking University 5Beijing Academy of Artificial Intelligence.
Pseudocode Yes Algorithm 1 PAR (Abstracted Version)
Open Source Code Yes Our code is publicly available at https://github.com/dmksjfl/PAR.
Open Datasets Yes We use four environments (halfcheetah, hopper, walker, ant) from Open AI Gym (Brockman et al., 2016) as source domains
Dataset Splits No The paper does not explicitly provide training/test/validation dataset splits, such as percentages or sample counts for each split, or reference predefined splits with citations for reproducibility.
Hardware Specification Yes CPU AMD EPYC 7452 GPU RTX3090 8 Memory 288GB
Software Dependencies No The paper mentions software like Open AI Gym, D4RL, SAC, DARC, VGDF, CQL, and the Adam optimizer, but does not provide specific version numbers for these software components or libraries.
Experiment Setup Yes Table 2. Detailed hyperparameter setup for PAR and baseline methods on the evaluated tasks.