Robust Learning from Demonstration Techniques and Tools

Authors: William Curran

AAAI 2016 | Conference PDF | Archive PDF | Plain Text | LLM Run Details

Reproducibility Variable Result LLM Response
Research Type Experimental We have shown the speed and robustness of this approach when combined with standard Q-Learning in the Mountaincar 3D (Figure 1) domain using good and bad demonstrations.
Researcher Affiliation Academia William Curran Oregon State University Corvallis, Oregon curranw@oregonstate.edu
Pseudocode No The paper describes algorithms and methods but does not include any explicit pseudocode blocks or algorithm figures.
Open Source Code No The paper does not state that the code for the developed methods (DRRL, IDRRL, or the movie-reel interface) is open-source, nor does it provide any links to a code repository.
Open Datasets No The paper mentions experiments in the
Dataset Splits No The paper does not provide specific dataset split information (exact percentages, sample counts, or citations to predefined splits) needed to reproduce the data partitioning.
Hardware Specification No The paper mentions the PR2 robot's physical specifications but does not provide any specific hardware details (e.g., GPU/CPU models, memory) used for running its experiments or training models.
Software Dependencies No The paper mentions software like RViz, ROS, Q-Learning, Oculus Rift, and Razer Hydra but does not provide specific version numbers for any of these software dependencies.
Experiment Setup No The paper does not contain specific experimental setup details such as concrete hyperparameter values, training configurations, or system-level settings.