Publications

@article{liu_leveraging_2024,

title = {Leveraging Organizational Hierarchy to Simplify Reward Design in Cooperative Multi-agent Reinforcement Learning},

author = {Lixing Liu and Volkan Ustun and Rajay Kumar},

url = {https://journals.flvc.org/FLAIRS/article/view/135588},

doi = {10.32473/flairs.37.1.135588},

issn = {2334-0762},

year  = {2024},

date = {2024-05-01},

urldate = {2024-08-13},

journal = {FLAIRS},

volume = {37},

abstract = {The effectiveness of multi-agent reinforcement learning (MARL) hinges largely on the meticulous arrangement of objectives. Yet, conventional MARL methods might not completely harness the inherent structures present in environmental states and agent relationships for goal organization. This study is conducted within the domain of military training simulations, which are typically characterized by complexity, heterogeneity, non-stationary and doctrine-driven environments with a clear organizational hierarchy and a top-down chain of command. This research investigates the approximation and integration of the organizational hierarchy into MARL for cooperative training scenarios, with the goal of streamlining the processes of reward engineering and enhancing team coordination. In the preliminary experiments, we employed two-tiered commander-subordinate feudal hierarchical (CSFH) networks to separate the prioritized team goal and individual goals. The empirical results demonstrate that the proposed framework enhances learning efficiency. It guarantees the learning of a prioritized policy for the commander agent and encourages subordinate agents to explore areas of interest more frequently, guided by appropriate soft constraints imposed by the commander.},

keywords = {Machine Learning},

pubstate = {published},

tppubtype = {article}

}

@article{koresh_improving_2024,

title = {Improving Reinforcement Learning Experiments in Unity through Waypoint Utilization},

author = {Caleb Koresh and Volkan Ustun and Rajay Kumar and Tim Aris},

url = {https://journals.flvc.org/FLAIRS/article/view/135571},

doi = {10.32473/flairs.37.1.135571},

issn = {2334-0762},

year  = {2024},

date = {2024-05-01},

urldate = {2024-08-13},

journal = {FLAIRS},

volume = {37},

abstract = {Multi-agent Reinforcement Learning (MARL) models teams of agents that learn by dynamically interacting with an environment and each other, presenting opportunities to train adaptive models for team-based scenarios. However, MARL algorithms pose substantial challenges due to their immense computational requirements. This paper introduces an automatically generated waypoint-based movement system to abstract and simplify complex environments in Unity while allowing agents to learn strategic cooperation. To demonstrate the effectiveness of our approach, we utilized a simple scenario with heterogeneous roles in each team. We trained this scenario on variations of realistic terrains and compared learning between fine-grained (almost) continuous and waypoint-based movement systems. Our results indicate efficiency in learning and improved performance with waypoint-based navigation. Furthermore, our results show that waypoint-based movement systems can effectively learn differentiated behavior policies for heterogeneous roles in these experiments. These early exploratory results point out the potential of waypoint-based navigation for reducing the computational costs of developing and training MARL models in complex environments. The complete project with all scenarios and results is available on GitHub: https://github.com/HATS-ICT/ml-agents-dodgeball-env-ICT.},

keywords = {Machine Learning},

pubstate = {published},

tppubtype = {article}

}

@article{awada_stress_2024,

title = {Stress appraisal in the workplace and its associations with productivity and mood: Insights from a multimodal machine learning analysis},

author = {Mohamad Awada and Burcin Becerik Gerber and Gale M. Lucas and Shawn C. Roll},

editor = {Iftikhar Ahmed Khan},

url = {https://dx.plos.org/10.1371/journal.pone.0296468},

doi = {10.1371/journal.pone.0296468},

issn = {1932-6203},

year  = {2024},

date = {2024-01-01},

urldate = {2024-02-21},

journal = {PLoS ONE},

volume = {19},

number = {1},

pages = {e0296468},

abstract = {Previous studies have primarily focused on predicting stress arousal, encompassing physiological, behavioral, and psychological responses to stressors, while neglecting the examination of stress appraisal. Stress appraisal involves the cognitive evaluation of a situation as stressful or non-stressful, and as a threat/pressure or a challenge/opportunity. In this study, we investigated several research questions related to the association between states of stress appraisal (i.e., boredom, eustress, coexisting eustress-distress, distress) and various factors such as stress levels, mood, productivity, physiological and behavioral responses, as well as the most effective ML algorithms and data signals for predicting stress appraisal. The results support the Yerkes-Dodson law, showing that a moderate stress level is associated with increased productivity and positive mood, while low and high levels of stress are related to decreased productivity and negative mood, with distress overpowering eustress when they coexist. Changes in stress appraisal relative to physiological and behavioral features were examined through the lenses of stress arousal, activity engagement, and performance. An XGBOOST model achieved the best prediction accuracies of stress appraisal, reaching 82.78% when combining physiological and behavioral features and 79.55% using only the physiological dataset. The small accuracy difference of 3% indicates that physiological data alone may be adequate to accurately predict stress appraisal, and the feature importance results identified electrodermal activity, skin temperature, and blood volume pulse as the most useful physiologic features. Implementing these models within work environments can serve as a foundation for designing workplace policies, practices, and stress management strategies that prioritize the promotion of eustress while reducing distress and boredom. Such efforts can foster a supportive work environment to enhance employee well-being and productivity.},

keywords = {DTIC, Machine Learning, UARC},

pubstate = {published},

tppubtype = {article}

}

@article{awada_predicting_2023,

title = {Predicting Office Workers’ Productivity: A Machine Learning Approach Integrating Physiological, Behavioral, and Psychological Indicators},

author = {Mohamad Awada and Burcin Becerik-Gerber and Gale Lucas and Shawn C. Roll},

url = {https://www.mdpi.com/1424-8220/23/21/8694},

doi = {10.3390/s23218694},

issn = {1424-8220},

year  = {2023},

date = {2023-10-01},

urldate = {2023-12-07},

journal = {Sensors},

volume = {23},

number = {21},

pages = {8694},

abstract = {This research pioneers the application of a machine learning framework to predict the perceived productivity of office workers using physiological, behavioral, and psychological features. Two approaches were compared: the baseline model, predicting productivity based on physiological and behavioral characteristics, and the extended model, incorporating predictions of psychological states such as stress, eustress, distress, and mood. Various machine learning models were utilized and compared to assess their predictive accuracy for psychological states and productivity, with XGBoost emerging as the top performer. The extended model outperformed the baseline model, achieving an R2 of 0.60 and a lower MAE of 10.52, compared to the baseline model’s R2 of 0.48 and MAE of 16.62. The extended model’s feature importance analysis revealed valuable insights into the key predictors of productivity, shedding light on the role of psychological states in the prediction process. Notably, mood and eustress emerged as significant predictors of productivity. Physiological and behavioral features, including skin temperature, electrodermal activity, facial movements, and wrist acceleration, were also identified. Lastly, a comparative analysis revealed that wearable devices (Empatica E4 and H10 Polar) outperformed workstation addons (Kinect camera and computer-usage monitoring application) in predicting productivity, emphasizing the potential utility of wearable devices as an independent tool for assessment of productivity. Implementing the model within smart workstations allows for adaptable environments that boost productivity and overall well-being among office workers.},

keywords = {DTIC, Machine Learning, UARC, Virtual Humans},

pubstate = {published},

tppubtype = {article}

}

@article{awada_new_2023,

title = {A New Perspective on Stress Detection: An Automated Approach for Detecting Eustress and Distress},

author = {Mohamad Awada and Burcin Becerik-Gerber and Gale Lucas and Shawn Roll and Ruying Liu},

url = {https://ieeexplore.ieee.org/document/10286408/},

doi = {10.1109/TAFFC.2023.3324910},

issn = {1949-3045, 2371-9850},

year  = {2023},

date = {2023-10-01},

urldate = {2023-12-07},

journal = {IEEE Trans. Affective Comput.},

pages = {1–15},

keywords = {DTIC, Machine Learning, UARC},

pubstate = {published},

tppubtype = {article}

}

@article{rodrigues_ergonomic_2022,

title = {Ergonomic assessment of office worker postures using 3D automated joint angle assessment},

author = {Patrick B. Rodrigues and Yijing Xiao and Yoko E. Fukumura and Mohamad Awada and Ashrant Aryal and Burcin Becerik-Gerber and Gale Lucas and Shawn C. Roll},

url = {https://linkinghub.elsevier.com/retrieve/pii/S1474034622000672},

doi = {10.1016/j.aei.2022.101596},

issn = {14740346},

year  = {2022},

date = {2022-04-01},

urldate = {2022-09-26},

journal = {Advanced Engineering Informatics},

volume = {52},

pages = {101596},

keywords = {DTIC, Machine Learning, UARC},

pubstate = {published},

tppubtype = {article}

}

@article{mell_expert-model_2021,

title = {An expert-model and machine learning hybrid approach to predicting human-agent negotiation outcomes in varied data},

author = {Johnathan Mell and Markus Beissinger and Jonathan Gratch},

url = {http://link.springer.com/10.1007/s12193-021-00368-w},

doi = {10.1007/s12193-021-00368-w},

issn = {1783-7677, 1783-8738},

year  = {2021},

date = {2021-03-01},

urldate = {2021-04-15},

journal = {J Multimodal User Interfaces},

abstract = {We present the results of a machine-learning approach to the analysis of several human-agent negotiation studies. By combining expert knowledge of negotiating behavior compiled over a series of empirical studies with neural networks, we show that a hybrid approach to parameter selection yields promise for designing more effective and socially intelligent agents. Specifically, we show that a deep feedforward neural network using a theory-driven three-parameter model can be effective in predicting negotiation outcomes. Furthermore, it outperforms other expert-designed models that use more parameters, as well as those using other techniques (such as linear regression models or boosted decision trees). In a follow-up study, we show that the most successful models change as the dataset size increases and the prediction targets change, and show that boosted decision trees may not be suitable for the negotiation domain. We anticipate these results will have impact for those seeking to combine extensive domain knowledge with more automated approaches in human-computer negotiation. Further, we show that this approach can be a stepping stone from purely exploratory research to targeted human-behavioral experimentation. Through our approach, areas of social artificial intelligence that have historically benefited from expert knowledge and traditional AI approaches can be combined with more recent proven-effective machine learning algorithms.},

keywords = {DTIC, Machine Learning, UARC, Virtual Humans},

pubstate = {published},

tppubtype = {article}

}