Search Results for author: Alberto Camacho

Found 5 papers, 0 papers with code

SparseDice: Imitation Learning for Temporally Sparse Data via Regularization

no code implementations ICML Workshop URL 2021 Alberto Camacho, Izzeddin Gur, Marcin Lukasz Moczulski, Ofir Nachum, Aleksandra Faust

We are concerned with a setting where the demonstrations comprise only a subset of state-action pairs (as opposed to the whole trajectories).

Imitation Learning

Disentangled Planning and Control in Vision Based Robotics via Reward Machines

no code implementations28 Dec 2020 Alberto Camacho, Jacob Varley, Deepali Jain, Atil Iscen, Dmitry Kalashnikov

In this work we augment a Deep Q-Learning agent with a Reward Machine (DQRM) to increase speed of learning vision-based policies for robot tasks, and overcome some of the limitations of DQN that prevent it from converging to good-quality policies.


Towards Neural-Guided Program Synthesis for Linear Temporal Logic Specifications

no code implementations31 Dec 2019 Alberto Camacho, Sheila A. McIlraith

Synthesizing a program that realizes a logical specification is a classical problem in computer science.

Program Synthesis

Finite LTL Synthesis with Environment Assumptions and Quality Measures

no code implementations31 Aug 2018 Alberto Camacho, Meghyn Bienvenu, Sheila A. McIlraith

In this paper, we investigate the problem of synthesizing strategies for linear temporal logic (LTL) specifications that are interpreted over finite traces -- a problem that is central to the automated construction of controllers, robot programs, and business processes.

Finite LTL Synthesis is EXPTIME-complete

no code implementations14 Sep 2016 Jorge A. Baier, Alberto Camacho, Christian Muise, Sheila A. McIlraith

LTL synthesis -- the construction of a function to satisfy a logical specification formulated in Linear Temporal Logic -- is a 2EXPTIME-complete problem with relevant applications in controller synthesis and a myriad of artificial intelligence applications.

Cannot find the paper you are looking for? You can Submit a new open access paper.