Learning State and Action Abstractions for Effective and Efficient Planning

Speaker: Rohan Chitnis , EECS, CSAIL

Date: Monday, April 25, 2022

Time: 10:30 AM to 11:30 AM Note: all times are in the Eastern Time Zone

Public: No

Location: 32-G449 (Patil/Kiva Seminar Room)

Event Type: Thesis Defense

Room Description:

Host: Tomas Lozano-Perez, Leslie Kaelbling, George Konidaris

Contact: Rohan Chitnis, ronuchit@mit.edu

Relevant URL:

Speaker URL: None

Speaker Photo:

Reminders to: seminars@csail.mit.edu

Reminder Subject: TALK: Thesis Defense - Rohan Chitnis, Learning State and Action Abstractions for Effective and Efficient Planning

Abstract: An autonomous agent should make good decisions quickly. These two considerations --- effectiveness and efficiency --- are especially important, and often competing, when an agent is planning to make decisions sequentially in long-horizon tasks. Unfortunately, planning directly in the state and action spaces of a task is highly intractable for many tasks of interest. Abstractions offer a mechanism to overcome this intractability, allowing the agent to reason at a higher level about the most salient aspects of a task. In this thesis, we develop novel frameworks for learning state and action abstractions that are optimized for both effective and efficient planning. Most generally, state and action abstractions are arbitrary transformations of the state and action spaces of the given planning problem; we focus on task-specific abstractions that leverage the structure of a given task (or family of tasks) to make planning efficient. In this talk, we show how to learn neuro-symbolic abstractions for bilevel planning, and demonstrate in robotic planning tasks that the methods we present optimize a tradeoff between planning effectively and planning efficiently.

Research Areas:
AI & Machine Learning

Impact Areas:

This event is not part of a series.

Created by Rohan Chitnis Email at Friday, February 11, 2022 at 1:09 PM.