Conference: AAAI 2020

 

From the 7 to the 12 of February I participated at the Thirty-Fourth AAAI Conference on Artificial Intelligence (AAAI-20) in New York.

During the conference, I attended the Turing Award Winners Event with the fathers of Deep Learning Yoshua Bengio, Geoffrey Hinton, and Yann LeCun, the invited speakers’ talks of Aude Billard and Stuart Russell, and AAAI/EAAI Panel about K-12 AI Education in 2020 with David Touretzky, Chistina Gardner-McCune, and Cynthia Breazeal. I also followed many great papers’ and posters’ presentations, some of them are listed below.

With other 18 Ph.D. students, I got selected for the Doctoral Consortium AAAI/SIGAI-20 led by Laura Hiatt and Shiwali Mohan.

The Doctoral Consortium provided me a unique opportunity to meet with major experts, such as my mentor Kartik Talamadupula, and other researchers from all over the world. Being part of the Doctoral Consortium was crucial for receiving thoughtful insights on my research and other related aspects – imposter syndrome included (thanks to Ayanna Howard).

I have never participated in a Doctoral Consortium before and I am glad I had this possibility in the flourishing research environment of the AAAI community. 

You can find some of the talks here.

Below a list of papers that I particularly appreciated:

• Explainable Reinforcement Learning Through a Causal Lens
• Off-Policy Evaluation in Partially Observable Environments
• AI for Explaining Decisions in Multi-Agent Environments
• Open-World Learning for Radically Autonomous Agents
• Learning to Model Opponent Learning (Student Abstract)
• Uncertainty-Aware Action Advising for Deep Reinforcement Learning Agents
• Improving Policies via Search in Cooperative Partially Observable Games
• CoCoX: Generating Conceptual and Counterfactual Explanations via Fault-Lines
• Expectation-Aware Planning: A Unifying Framework for Synthesizing and Executing Self-Explaining Plans for Human-Aware Planning
• AISpace2: An Interactive Visualization Tool for Learning and Teaching Artificial Intelligence

 

Tutorials:

• Explainable AI: Foundations, Industrial Applications, Practical Challenges, and Lessons Learned
• Synthesizing Explainable and Deceptive Behavior for Human-AI Interaction
• Representation Learning for Causal Inference
• Exploration-Exploitation in Reinforcement Learning

 

Repositories:

• An interactive conversational agent for AI education
• The ROSPlan framework for task planning in a ROS system