Portfolio item number 1
Short description of portfolio item number 1
Posts by Collection
portfolio
Portfolio item number 2
Short description of portfolio item number 2
publications
Story Shaping: Teaching Agents Human-like Behavior with Stories
Published in AIIDE, 2023
Reward design for reinforcement learning agents is challenging when the method of achieving goals matters, such as adhering to commonsense or specific behavioral preferences. We introduce Story Shaping, a new technique, to help agents infer and align their actions with tacit knowledge from exemplar stories, using knowledge graphs to generate intrinsic rewards based on the similarity between the agent actions and the story world.
Neural Story Planning
Published in The AAAI-23 Workshop on Creative AI Across Modalities, 2023
We present a method for story plot generation that combines causal planning with neural language models. By using commonsense knowledge to recursively expand story plots in a backward chaining fashion, our system improves narrative coherence. Automatic evaluations show that this approach generates more coherent plotlines than several strong baselines.
Examinator v3.0: Cheating Detection in Online Take-Home Exams
Published in Proceedings of the Tenth ACM Conference on Learning@ Scale, 2023
Examinator v3.0 detects cheating in online take-home exams by comparing answers and the timestamps they were entered. A web interface enables efficient manual inspection. Use of the tool reveals that certain question types substantially enhance cheating detection, demonstrating the potential of automated algorithmic detection at scale. Examinator v3.0 has analyzed 915,831 pairs of exam submissions across three courses over two semesters at a top U.S. institution, identifying 46 instances of cheating.
Thespian: Multi-Character Text Role-Playing Game Agents
Published in Proceedings of the AIIDE Workshop on Experimental AI in Games, 2023
Text-adventure and text role-playing games pose significant challenges for reinforcement learning agents. We introduce a “thespian agent” framework that can emulate multiple characters, using a soft prompt for direction and an attention mechanism for few-shot learning. Our agent surpasses the current state-of-the-art in multi-character and few-shot learning.
talks
Talk 1 on Relevant Topic in Your Field
Published:
This is a description of your talk, which is a markdown files that can be all markdown-ified like any other post. Yay markdown!
Conference Proceeding talk 3 on Relevant Topic in Your Field
Published:
This is a description of your conference proceedings talk, note the different field in type. You can put anything in this field.
teaching
Graduate Teaching Assistant
Graduate Course, Georgia Institute of Technology, College of Computing, 2022
From August 2022 to May 2023, I served as a Graduate Teaching Assistant for the class CS6601: Artificial Intelligence under Dr. Thomas Ploetz in Fall 2022 and for the classes CS6601: Artificial Intelligence and CS3600: Introduction to Artificial Intelligence under Dr. Thad Starner in Spring 2023. My duties included but were not limited to:
Graduate Teaching Assistant
Graduate Course, Georgia Institute of Technology, College of Computing, 2023
In Summer of 2023, I served as a Graduate Teaching Assistant for the class CS7650: Natural Language Processsing under Dr. Mark Riedl. My duties included but were not limited to:
Head Graduate Teaching Assistant
Graduate Course, Georgia Institute of Technology, College of Computing, 2023
From August 2023, I served as the Head Graduate Teaching Assistant for the class CS6601: Artificial Intelligence under Dr. Thomas Ploetz in Fall 2023 and for the classes CS6601: Artificial Intelligence and CS3600: Introduction to Artificial Intelligence under Dr. Thad Starner in Spring 2024. I am currently a Head Graduate Teaching Assistant for Dr. Rodrigo Borela Valente for CS6601: Artificial Intelligence in Summer 2024. My duties included but are not limited to: