Cross-domain Imitation from Observations

Authors: Dripta S. Raychaudhuri, Sujoy Paul, Jeroen Vanbaar, Amit K. Roy-Chowdhury

ICML 2021 | Conference PDF | Archive PDF | Plain Text | LLM Run Details

Reproducibility Variable Result LLM Response
Research Type Experimental Experiments across a wide variety of challenging domains demonstrate the efficacy of our approach.
Researcher Affiliation Collaboration 1University of California, Riverside 2Google Research 3Mitsubishi Electric Research Laboratories
Pseudocode Yes Algorithm 1 Learn domain transformation ψ
Open Source Code Yes Code and videos are available at: https://driptarc.github.io/xdio.html.
Open Datasets No The paper describes generating trajectories within environments like MuJoCo and OpenAI Gym, but it does not provide a specific link, DOI, repository, or formal citation for a pre-collected, publicly available dataset used for training. The data is generated dynamically.
Dataset Splits No The paper does not explicitly state specific percentages or counts for training, validation, and test splits. It mentions collecting 'a dataset of state-action triplets P = {(st A, at A, st+1 A )} by random exploration' but does not specify how this or other data is split.
Hardware Specification No The paper does not provide specific hardware details such as GPU or CPU models used for running the experiments. It only mentions using the MuJoCo physics engine.
Software Dependencies No The paper mentions software like MuJoCo and Open AI Gym, and algorithms like PPO and A3C, but does not specify version numbers for any of these components, which is required for reproducible software dependency information.
Experiment Setup No The paper states, 'Implementation details are presented in the supplementary materials.' This indicates that specific experimental setup details, such as hyperparameters or training configurations, are not provided in the main text of the paper.