197,298 research outputs found
Atari-HEAD: Atari Human Eye-Tracking and Demonstration Dataset
No full textVersion 4 of the dataset is available (Sep 19 2019)!
Note this version has significantly more data than Version 2.
Dataset description paper (full version) is available!
https://arxiv.org/pdf/1903.06754.pdf (updated Sep 7 2019)
Tools for visualizing the data is available!
https://github.com/corgiTrax/Gaze-Data-Processor
=========================== Dataset Description ===========================
We provide a large-scale, high-quality dataset of human actions with simultaneously recorded eye movements while humans play Atari video games. The dataset consists of 117 hours of gameplay data from a diverse set of 20 games, with 8 million action demonstrations and 328 million gaze samples. We introduce a novel form of gameplay, in which the human plays in a semi-frame-by-frame manner. This leads to near-optimal game decisions and game scores that are comparable or better than known human records. For every game frame, its corresponding image frame, the human keystroke action, the reaction time to make that action, the gaze positions, and immediate reward returned by the environment were recorded.
Q & A: Why frame-by-frame game mode?
Resolving state-action mismatch: Closed-loop human visuomotor reaction time is around 250-300 milliseconds. Therefore, during gameplay, state (image) and action that are simultaneously recorded at time step t could be mismatched. Action at time t could be intended for a state 250-300ms ago. This effect causes a serious issue for supervised learning algorithms, since label at and input st are no longer matched. Frame-by-frame game play ensures states and actions are matched at every timestep.
Maximizing human performance: Frame-by-frame mode makes gameplay more relaxing and reduces fatigue, which could normally result in blinking and would corrupt eye-tracking data. More importantly, this design reduces sub-optimal decisions caused by inattentive blindness.
Highlighting critical states that require multiple eye movements: Human decision time and all eye movements were recorded at every frame. The states that could lead to a large reward or penalty, or the ones that require sophisticated planning, will take longer and require multiple eye movements for the player to make a decision. Stopping gameplay means that the observer can use eye-movements to resolve complex situations. This is important because if the algorithm is going to learn from eye-movements it must contain all “relevant” eye-movements.
============================ Readme ============================
1. meta_data.csv: meta data for the dataset., including:
GameName: String. Game name. e.g., “alien” indicates the trial is collected for game Alien (15 min time limit). “alien_highscore” is the trajectory collected from the best player’s highest score (2 hour limit). See dataset description paper for details.
trial_id: Integer. One can use this number to locate the associated .tar.bz2 file and label file.
subject_id: Char. Human subject identifiers.
load_trial: Integer. 0 indicates that the game starts from scratch. If this field is non-zero, it means that the current trial continues from a saved trial. The number indicates the trial number to look for.
highest_score: Integer. The highest game score obtained from this trial.
total_frame: Number of image frames in the .tar.bz2 repository.
total_game_play_time: Integer. game time in ms.
total_episode: Integer. number of episodes in the current trial. An episode terminates when all lives are consumed.
avg_error: Float. Average eye-tracking validation error at the end of each trial in visual degree (1 visual degree = 1.44 cm in our experiment). See our paper for the calibration/validation process.
max_error: Float. Max eye-tracking validation error.
low_sample_rate: Percentage. Percentage of frames with less than 10 gaze samples. The most common reason for this is blinking.
frame_averaging: Boolean. The game engine allows one to turn this on or off. When turning on (TRUE), two consecutive frames are averaged, this alleviates screen flickering in some games.
fps: Integer. Frame per second when an action key is held down.
2. [game_name].zip files: these include data for each game, including:
*.tar.bz2 files: contains game image frames. The filename indicates its trial number.
*.txt files: label file for each trial, including:
frame_id: String. The ID of a frame, can be used to locate the corresponding image frame in .tar.bz2 file.
episode_id: Integer (not available for some trials). Episode number, starting from 0 for each trial. A trial could contain a single trial or multiple trials.
score: Integer (not available for some trials). Current game score for that frame.
duration(ms): Integer. Time elapsed until the human player made a decision.
unclipped_reward: Integer. Immediate reward returned by the game engine.
action: Integer. See action_enums.txt for the mapping. This is consistent with the Arcade Learning Environment setup.
gaze_positions: Null/A list of integers: x0,y0,x1,y1,...,xn,yn. Gaze positions for the current frame. Could be null if no gaze. (0,0) is the top-left corner. x: horizontal axis. y: vertical.
3. action_enums.txt: contains integer to action mapping defined by the Arcade Learning Environment.
============================ Citation ============================
If you use the Atari-HEAD in your research, we ask that you please cite the following:
@misc{zhang2019atarihead,
title={Atari-HEAD: Atari Human Eye-Tracking and Demonstration Dataset},
author={Ruohan Zhang and Calen Walshe and Zhuode Liu and Lin Guan and Karl S. Muller and Jake A. Whritner and Luxin Zhang and Mary M. Hayhoe and Dana H. Ballard},
year={2019},
eprint={1903.06754},
archivePrefix={arXiv},
primaryClass={cs.LG}
}
Zhang, Ruohan, Zhuode Liu, Luxin Zhang, Jake A. Whritner, Karl S. Muller, Mary M. Hayhoe, and Dana H. Ballard. "AGIL: Learning attention from human for visuomotor tasks." In Proceedings of the European Conference on Computer Vision (ECCV), pp. 663-679. 2018.
@inproceedings{zhang2018agil,
title={AGIL: Learning attention from human for visuomotor tasks},
author={Zhang, Ruohan and Liu, Zhuode and Zhang, Luxin and Whritner, Jake A and Muller, Karl S and Hayhoe, Mary M and Ballard, Dana H},
booktitle={Proceedings of the European Conference on Computer Vision (ECCV)},
pages={663--679},
year={2018}
}
</p
Circuit Bodging: Atari Punk Console
No full textCircuit bodging is back! Maxwell is proud to present small, simple, but ultimately lovable little circuits to build for your own, personal pleasure. In this edition we are featuring: The Atari Punk Console. The Atari Punk Console (or APC) is a 555 timer IC based noise maker circuit. The original was designed by Forrest M. Mims III, and published in his book “Engineer’s Mini-Notebook - 555 Circuits” (Siliconcepts, 1984). It uses two 555 timers to create a variable pulse width oscillator with a similar sound to the infamous Atari 2600.Electrical Engineering, Mathematics and Computer Scienc
Atari-HEAD: Atari Human Eye-Tracking and Demonstration Dataset
No full text<p>We introduce a large-scale dataset of human actions and eye movements while playing Atari videos games. Human subjects play games in a frame-by-frame manner to allow enough decision time in order to obtain near-optimal decisions.</p>
<p>For every game frame, its corresponding image frame, the human keystroke action, the reaction time to make that action, the gaze positions, and immediate reward returned by the environment were recorded. The gaze data was recorded using an EyeLink 1000 eye tracker at 1000Hz. The human subjects are amateur players who are familiar with the games. The human subjects were only allowed to play for 15 minutes and were required to rest for at least 15 minutes before the next trial. We collected data from 4 subjects, 16 games, 175 15-minute trials, and a total of 2.97 million frames/demonstrations. </p>
<p> </p>
<p>1. meta_data.csv: meta data for the dataset. Data fields:</p>
<p>Game: String. Game name.</p>
<p>TrialNumber: Integer. One can use this number to locate the associated .tar.bz2 file and label file.</p>
<p>SubjID: Char. Human subject identifiers.</p>
<p>Load: Integer. 0 indicates that the game starts from scratch. If this field is non-zero, it means that the current trial continues from a saved trial. The number indicates the trial number to look for.</p>
<p>FrameAveraging: Boolean. The game engine allows one to turn this on or off. When turning on (TRUE), two consecutive frames are averaged, this alleviates screen flickering in some games.</p>
<p>FPS: Integer. Frame per second when an action key is held down.</p>
<p>NumberOfFrames: Number of image frames in the .tar.bz2 repository.</p>
<p>AverageValError: Float. Eye-tracking validation error at the end of each trial in visual degree (1 visual degree = 1.44 cm in our experiment).</p>
<p>BestScore: Integer. The highest game score obtained from this trial.</p>
<p>2. *.tar.bz2 files: contains game image frames. The filename indicates its trial number.</p>
<p>3. *.txt files: label file for each trial. Data fields include:</p>
<p>frame_id: String. The ID of a frame, can be used to locate the corresponding image frame in .tar.bz2 file.</p>
<p>episode_id: Integer (not available for some trials). Episode number, starting from 0 for each trial. A trial could contain a single trial or multiple trials.</p>
<p>score: Integer (not available for some trials). Current game score for that frame.</p>
<p>duration(ms): Integer. Time elapsed until the human player made a decision. </p>
<p>unclipped_reward: Integer. Immediate reward returned by the game engine.</p>
<p>action: Integer. See action_enums.txt for the mapping. This is consistent with the Arcade Learning Environment setup.</p>
<p>gaze_positions: Null/A list of integers: x0,y0,x1,y1,...,xn,yn. Gaze positions for the current frame. Could be null if no gaze. (0,0) is the top-left corner. x: horizontal axis. y: vertical.</p>
<p> </p>
<p>If you use the Atari-HEAD in your research, we ask that you please cite the following:</p>
<p>Zhang, Ruohan, Zhuode Liu, Luxin Zhang, Jake A. Whritner, Karl S. Muller, Mary M. Hayhoe, and Dana H. Ballard. "AGIL: Learning attention from human for visuomotor tasks." In <em>Proceedings of the European Conference on Computer Vision (ECCV)</em>, pp. 663-679. 2018.</p>
<pre>@inproceedings{zhang2018agil,
title={AGIL: Learning attention from human for visuomotor tasks},
author={Zhang, Ruohan and Liu, Zhuode and Zhang, Luxin and Whritner, Jake A and Muller, Karl S and Hayhoe, Mary M and Ballard, Dana H},
booktitle={Proceedings of the European Conference on Computer Vision (ECCV)},
pages={663--679},
year={2018}
}</pre>
Width-based Lookaheads with Learnt Base Policies and Heuristics Over the Atari-2600 Benchmark
No full textWe propose new width-based planning and learning algorithms applied over the Atari-2600 benchmark. The algorithms presented are inspired from a careful analysis of the design decisions made by previous width-based planners. We benchmark our new algorithms over the Atari-2600 games and show that our best performing algorithm, RIW C +CPV, outperforms previously introduced width-based planning and learning algorithms π -IW(1), π -IW(1)+ and π -HIW(n, 1). Furthermore, we present a taxonomy of the set of Atari-2600 games according to some of their defining characteristics. This analysis of the games provides further insight into the behaviour and performance of the width-based algorithms introduced. Namely, for games with large branching factors, and games with sparse meaningful rewards, RIW C +CPV outperforms π -IW, π -IW(1)+ and
π -HIW(n, 1)
Dr. Duane M. Jackson, Morehouse College, July 2011
No full textThis video is a conversation with Dr. Duane M. Jackson. Dr. Jackson talks about his paper, "Recall and the Serial Position Effect: The Role of Primacy and Recency on Accounting Students' Performance." Jackie Daniel, AUC Woodruff Library, is the interviewer
"Reflections on the subject of Emigration from Europe with a view to Settlement in the United States" By M. Carey.
No full text"Reflections on the subject of Emigration from Europe with a view to Settlement in the United States: containing bried sketches of the moral and political character of those states.
By M. Carey, member of the American philosophical, and of the American Antiquarian Society, and author of The Olive Branch, Cindiciae Hibernicae, essays on banking, on political economy, and on internal improvement.
To which are now added the English editor's comments on the subject; together with Important Advice to Emigrants, and Cautions Against Impositions Practiced in the Outports
Dispelling the Myths Behind First-author Citation Counts
No full textWe conducted a full-scale evaluative citation analysis study of scholars in the XML research field to explore just how different from each other author rankings resulting from different citation counting methods actually are, and to demonstrate the capability of emerging data and tools on the Web in supporting more realistic citation counting methods. Our results contest some common arguments for the continued
use of first-author citation counts in the evaluation of scholars, such as high correlations between author rankings by first-author citation counts and other citation
counting methods, and high costs of using more realistic citation counting methods that are not well-supported by the ISI databases. It is argued that increasingly available digital full text research papers make it possible for citation analysis studies to go beyond what the ISI databases have directly supported and to employ more
sophisticated methods
Dr. Glendon Swarthout
No full textHosted by Roger M. Busfield, MSU Assistant Professor of Speech and Theater, Meet the Author is designed to introduce a general audience to a contemporary author and their work through in-depth interviews. This episode features a conversation between Dr. Glendon Swarthout, prolific author and English professor at MSU, and assistant professors Sam S. Baskett and Theodore B. Strandness
Visual rationalizations in deep reinforcement learning for Atari games
No full textDue to the capability of deep learning to perform well in high dimensional problems, deep reinforcement learning agents perform well in challenging tasks such as Atari 2600 games. However, clearly explaining why a certain action is taken by the agent can be as important as the decision itself. Deep reinforcement learning models, as other deep learning models, tend to be opaque in their decision-making process. In this work, we propose to make deep reinforcement learning more transparent by visualizing the evidence on which the agent bases its decision. In this work, we emphasize the importance of producing a justification for an observed action, which could be applied to a black-box decision agent
Simulation of thermal plant optimization and hydraulic aspects of thermal distribution loops for large campuses
No full textFollowing an introduction, the author describes Texas A&M University and its utilities system. After that, the author presents how to construct simulation models for chilled water and heating hot water distribution systems. The simulation model was used in a $2.3 million Ross Street chilled water pipe replacement project at Texas A&M University. A second project conducted at the University of Texas at San Antonio was used as an example to demonstrate how to identify and design an optimal distribution system by using a simulation model. The author found that the minor losses of these closed loop thermal distribution systems are significantly higher than potable water distribution systems. In the second part of the report, the author presents the latest development of software called the Plant Optimization Program, which can simulate cogeneration plant operation, estimate its operation cost and provide optimized operation suggestions. The author also developed detailed simulation models for a gas turbine and heat recovery steam generator and identified significant potential savings. Finally, the author also used a steam turbine as an example to present a multi-regression method on constructing simulation models by using basic statistics and optimization algorithms. This report presents a survey of the author??s working experience at the Energy Systems Laboratory (ESL) at Texas A&M University during the period of January 2002 through March 2004. The purpose of the above work was to allow the author to become familiar with the practice of engineering. The result is that the author knows how to complete a project from start to finish and understands how both technical and nontechnical aspects of a project need to be considered in order to ensure a quality deliverable and bring a project to successful completion. This report concludes that the objectives of the internship were successfully accomplished and that the requirements for the degree of Degree of Engineering have been satisfied
- …
