Dataset for Paper "The EMPATHIC Framework for Task Learning from Implicit Human Feedback"

<p>This is the <strong>raw</strong> data set for the&nbsp;paper &quot;The EMPATHIC Framework for Task Learning from Implicit Human Feedback&quot;, published at CoRL 2020. (<a href="https://sites.google.com/utexas.edu/empathic/home">project website</a>)</p> <p>The data set contains human facial reactions&nbsp;recorded while the subjects watching autonomous agents completing a task that determines their reward. This&nbsp;data set contains&nbsp;data recorded in two domains: <em>Robotaxi</em> and <em>RoboticSortingTask</em> (details of each domain can be found in the paper).</p> <p>This data set file&nbsp;is organized as:</p> <ul> <li><strong>RobotaxiData</strong>/: <ul> <li>subject_id/ <ul> <li>episode_N/ <ul> <li>[subject_id]_episode_N_[time]_[time_step]_[frame_id].jpg</li> </ul> </li> </ul> </li> <li>RLstatistics_episode_N.csv: time_step, reward, optimality</li> </ul> </li> <li><strong>RoboticSortingTaskData</strong>/ <ul> <li>subject_id/ <ul> <li>[subject_id]_[trajectory_order]_[trajectory_id]</li> </ul> </li> <li>trajectory_returns.csv: trajectory_id, final_return</li> </ul> </li> </ul> <p>If you find this data set useful for your research, please consider citing&nbsp;our paper:</p> <pre>@inproceedings{cui2020empathic, title={The EMPATHIC Framework for Task Learning from Implicit Human Feedback}, author={Cui, Yuchen and Zhang, Qiping and Allievi, Alessandro and Stone, Peter and Niekum, Scott and Knox, W Bradley}, booktitle={Conference on Robot Learning}, year={2020}, organization={PMLR} }</pre> <p>&nbsp;</p>