Towards Building Autonomous Agents that Handle Open-World Environments

April 4, 2022
4:00 pm ET
Cummings 435, Zoom
Speaker: Shivam Goel
Host: Jivko Sinapov


Quals talk:

Artificial Intelligence agents have shown exceptional performance in many closed worlds domains such as games where the action space, state space, and the transition dynamics are fixed for duration of the task. Even minor changes in the environment dynamics, however, can lead to catastrophic results for closed-world agents. To make the agents more suitable for a real-world setting, we need to relax closed-world assumptions and make agents robust to novel, unseen, and unexpected scenarios. To build agents more robust to unseen scenarios we propose (1) A novel experimental environment called NovelGridworlds to benchmark and develop such agents which can respond to novelties. (2) A novel architecture called RAPid-Learn which synergistically integrates planning and learning methodologies to learn to best respond to the sudden and unexpected changes in an agent's environment (i.e., novelties). In this talk, I will present the details of the proposed experimental environment and show results of the proposed architecture. I will also discuss the improvements and future work of this research.

Research area: Reinforcement Learning, Robotics, Symbolic Learning

Please join meeting in JCC 435 or join via Zoom.

Join Zoom Meeting:

Password: See colloquium email

Dial-in not an option for this event.