Sanjit Seshia

Ashera: Neural Optimization Modulo Theories

Overview:

Ashera is a state-of-the-art Optimization Modulo Theory (OMT) solver, which explicitly targets a rising class of optimization problems such as multi-agent traveling salesman (mTSP) and multi-resource DAG scheduling. We excel at disjunctive problems which lead to well studied failure modes for ILP solvers exploiting both Logical Neighborhood Search and Neural Diving.

Logical Neighborhood Search decouples combinatorial search with convex optimization. For any feasible solution, Ashera performs convex optimization within...

Formal Skill Representation and Composition for Task Generalization

Abstract

In this work, we focus on developing a methodology to systematically generate challenging scenarios to assist RL agents generalize their ability to solve a task in autonomous driving domain. First, we derive our scenarios from autonomous vehicles (AVs) crash reports in California Department of Motor Vehicles (DMV). These scenarios will serve as realistic training environments for RL agents and learning to drive in these challenging scenarios could help generalize their ability to drive. More specifically, using natural language processing...

Automating Multi-Agent Curriculum Learning with Probabilistic Programs

Abstract

Automatic curriculum learning (ACL) is a family of mechanisms that automatically adapt the distribution of training data by learning to adjust the selection of learning situations to the capabilities of deep reinforcement learning (RL) agents. ACL can be practically beneficial to enhance not only the training sample efficiency but also RL agents' capabilities to achieve harder tasks via incrementally challenging and diverse curriculum. In this work, we focus on scenario generation, or procedural content generation, to automatically create a...