1 code implementation • 15 May 2023 • Achille Fokoue, Ibrahim Abdelaziz, Maxwell Crouse, Shajith Ikbal, Akihiro Kishimoto, Guilherme Lima, Ndivhuwo Makondo, Radu Marinescu
NIAGRA addresses this problem by using 1) improved Graph Neural Networks for learning name-invariant formula representations that is tailored for their unique characteristics and 2) an efficient ensemble approach for automated theorem proving.
1 code implementation • 30 Aug 2023 • Jasmina Gajcin, James McCarthy, Rahul Nair, Radu Marinescu, Elizabeth Daly, Ivana Dusparic
Our approach allows the user to provide trajectory-level feedback on agent's behavior during training, which can be integrated as a reward shaping signal in the following training iteration.
no code implementations • 15 Jan 2014 • Robert Mateescu, Rina Dechter, Radu Marinescu
We provide two algorithms for compiling the AOMDD of a graphical model.
no code implementations • NeurIPS 2018 • Hao Cui, Radu Marinescu, Roni Khardon
This yields a novel algebraic gradient-based solver (AGS) for MMAP.
no code implementations • NeurIPS 2015 • Akihiro Kishimoto, Radu Marinescu, Adi Botea
The paper presents and evaluates the power of parallel search for exact MAP inference in graphical models.
no code implementations • 2 Feb 2019 • Adi Botea, Christian Muise, Shubham Agarwal, Oznur Alkan, Ondrej Bajgar, Elizabeth Daly, Akihiro Kishimoto, Luis Lastras, Radu Marinescu, Josef Ondrej, Pablo Pedemonte, Miroslav Vodolan
Dialogue systems have many applications such as customer support or question answering.
no code implementations • NeurIPS 2019 • Radu Marinescu, Rina Dechter
We introduce #opt, a new inference task for graphical models which calls for counting the number of optimal solutions of the model.
no code implementations • 2 Jul 2021 • Paulito P. Palmes, Akihiro Kishimoto, Radu Marinescu, Parikshit Ram, Elizabeth Daly
The pipeline optimization problem in machine learning requires simultaneous optimization of pipeline structures and parameter adaptation of their elements.
no code implementations • 25 Sep 2021 • Haifeng Qian, Radu Marinescu, Alexander Gray, Debarun Bhattacharjya, Francisco Barahona, Tian Gao, Ryan Riegel, Pravinda Sahu
This paper introduces Logical Credal Networks, an expressive probabilistic logic that generalizes many prior models that combine logic and probability.
no code implementations • ICML Workshop AutoML 2021 • Akihiro Kishimoto, Djallel Bouneffouf, Radu Marinescu, Parikshit Ram, Ambrish Rawat, Martin Wistuba, Paulito Pedregosa Palmes, Adi Botea
Optimizing a machine learning (ML) pipeline has been an important topic of AI and ML.
no code implementations • 17 Dec 2021 • Jasmina Gajcin, Rahul Nair, Tejaswini Pedapati, Radu Marinescu, Elizabeth Daly, Ivana Dusparic
In complex tasks where the reward function is not straightforward and consists of a set of objectives, multiple reinforcement learning (RL) policies that perform task adequately, but employ different strategies can be trained by adjusting the impact of individual objectives on reward function.
no code implementations • LNLS (ACL) 2022 • Ryokan Ri, Yufang Hou, Radu Marinescu, Akihiro Kishimoto
When mapping a natural language instruction to a sequence of actions, it is often useful toidentify sub-tasks in the instruction.
no code implementations • 18 Jul 2022 • James McCarthy, Rahul Nair, Elizabeth Daly, Radu Marinescu, Ivana Dusparic
Explainability of Reinforcement Learning (RL) policies remains a challenging research problem, particularly when considering RL in a safety context.
no code implementations • 19 Feb 2023 • Daniel Karl I. Weidele, Shazia Afzal, Abel N. Valente, Cole Makuch, Owen Cornec, Long Vu, Dharmashankar Subramanian, Werner Geyer, Rahul Nair, Inge Vejsbjerg, Radu Marinescu, Paulito Palmes, Elizabeth M. Daly, Loraine Franke, Daniel Haehn
AutoDOViz seeks to lower the barrier of entry for data scientists in problem specification for reinforcement learning problems, leverage the benefits of AutoDO algorithms for RL pipeline search and finally, create visualizations and policy insights in order to facilitate the typical interactive nature when communicating problem formulation and solution proposals between DO experts and domain experts.
no code implementations • 31 Aug 2023 • Bobak Pezeshki, Radu Marinescu, Alexander Ihler, Rina Dechter
Scientific computing has experienced a surge empowered by advancements in technologies such as neural networks.
no code implementations • 2 Feb 2024 • Debarun Bhattacharjya, JunKyu Lee, Don Joven Agravante, Balaji Ganesan, Radu Marinescu
Foundation models (FMs) such as large language models have revolutionized the field of AI by showing remarkable performance in various tasks.