Andre Beckus
YOU?
Author Swipe
View article: Airlift Challenge: A Competition for Optimizing Cargo Delivery
Airlift Challenge: A Competition for Optimizing Cargo Delivery Open
Airlift operations require the timely distribution of various cargo, much of which is time sensitive and valuable. These operations, however, have to contend with sudden disruptions from weather and malfunctions, requiring immediate resche…
View article: Automaton Distillation: Neuro-Symbolic Transfer Learning for Deep Reinforcement Learning
Automaton Distillation: Neuro-Symbolic Transfer Learning for Deep Reinforcement Learning Open
Reinforcement learning (RL) is a powerful tool for finding optimal policies in sequential decision processes. However, deep RL methods have two weaknesses: collecting the amount of agent experience required for practical RL problems is pro…
View article: On the Robustness of AlphaFold: A COVID-19 Case Study
On the Robustness of AlphaFold: A COVID-19 Case Study Open
Protein folding neural networks (PFNNs) such as AlphaFold predict remarkably accurate structures of proteins compared to other approaches. However, the robustness of such networks has heretofore not been explored. This is particularly rele…
View article: Sketch-based community detection in evolving networks
Sketch-based community detection in evolving networks Open
We consider an approach for community detection in time-varying networks. At its core, this approach maintains a small sketch graph to capture the essential community structure found in each snapshot of the full network. We demonstrate how…
View article: Inferring Probabilistic Reward Machines from Non-Markovian Reward Signals for Reinforcement Learning
Inferring Probabilistic Reward Machines from Non-Markovian Reward Signals for Reinforcement Learning Open
The success of reinforcement learning in typical settings is predicated on Markovian assumptions on the reward signal by which an agent learns optimal policies. In recent years, the use of reward machines has relaxed this assumption by ena…
View article: Multi-Agent Tree Search with Dynamic Reward Shaping
Multi-Agent Tree Search with Dynamic Reward Shaping Open
Sparse rewards and their representation in multi-agent domains remains a challenge for the development of multi-agent planning systems. While techniques from formal methods can be adopted to represent the underlying planning objectives, th…
View article: Steady-State Planning in Expected Reward Multichain MDPs
Steady-State Planning in Expected Reward Multichain MDPs Open
The planning domain has experienced increased interest in the formal synthesis of decision-making policies. This formal synthesis typically entails finding a policy which satisfies formal specifications in the form of some well-defined log…
View article: Learning Probabilistic Reward Machines from Non-Markovian Stochastic Reward Processes.
Learning Probabilistic Reward Machines from Non-Markovian Stochastic Reward Processes. Open
The success of reinforcement learning in typical settings is, in part, predicated on underlying Markovian assumptions on the reward signal by which an agent learns optimal policies. In recent years, the use of reward machines has relaxed t…
View article: Inferring Probabilistic Reward Machines from Non-Markovian Reward Processes for Reinforcement Learning
Inferring Probabilistic Reward Machines from Non-Markovian Reward Processes for Reinforcement Learning Open
The success of reinforcement learning in typical settings is predicated on Markovian assumptions on the reward signal by which an agent learns optimal policies. In recent years, the use of reward machines has relaxed this assumption by ena…
View article: Controller Synthesis for Omega-Regular and Steady-State Specifications
Controller Synthesis for Omega-Regular and Steady-State Specifications Open
Given a Markov decision process (MDP) and a linear-time ($ω$-regular or LTL) specification, the controller synthesis problem aims to compute the optimal policy that satisfies the specification. More recently, problems that reason over the …
View article: Dynamic Automaton-Guided Reward Shaping for Monte Carlo Tree Search
Dynamic Automaton-Guided Reward Shaping for Monte Carlo Tree Search Open
Reinforcement learning and planning have been revolutionized in recent years, due in part to the mass adoption of deep convolutional neural networks and the resurgence of powerful methods to refine decision-making policies. However, the pr…
View article: Verifiable Planning in Expected Reward Multichain MDPs.
Verifiable Planning in Expected Reward Multichain MDPs. Open
The planning domain has experienced increased interest in the formal synthesis of decision-making policies. This formal synthesis typically entails finding a policy which satisfies formal specifications in the form of some well-defined log…
View article: Sketch-based community detection in evolving networks
Sketch-based community detection in evolving networks Open
We consider an approach for community detection in time-varying networks. At its core, this approach maintains a small sketch graph to capture the essential community structure found in each snapshot of the full network. We demonstrate how…
View article: Steady-State Policy Synthesis in Multichain Markov Decision Processes
Steady-State Policy Synthesis in Multichain Markov Decision Processes Open
The formal synthesis of automated or autonomous agents has elicited strong interest from the artificial intelligence community in recent years. This problem space broadly entails the derivation of decision-making policies for agents acting…
View article: Scalable and Robust Community Detection with Randomized Sketching
Scalable and Robust Community Detection with Randomized Sketching Open
This article explores and analyzes the unsupervised clustering of large partially observed graphs. We propose a scalable and provable randomized framework for clustering graphs generated from the stochastic block model. The clustering is f…
View article: Passive Scene Reconstruction in Non-line-of-sight Scenarios
Passive Scene Reconstruction in Non-line-of-sight Scenarios Open
Locating and identifying hidden objects can prove critical in applications ranging from military reconnaissance to emergency rescue. Although non-line-of-sight (NLOS) reconstruction and imaging have received much attention recently, state-…
View article: Multi-Modal Non-Line-of-Sight Passive Imaging
Multi-Modal Non-Line-of-Sight Passive Imaging Open
We consider the non-line-of-sight (NLOS) imaging of an object using the light reflected off a diffusive wall. The wall scatters incident light such that a lens is no longer useful to form an image. Instead, we exploit the 4D spatial cohere…
View article: Randomized Robust Matrix Completion for the Community Detection Problem
Randomized Robust Matrix Completion for the Community Detection Problem Open
This paper explores and analyzes the unsupervised clustering of large partially observed graphs. We propose a scalable and provable randomized framework for clustering graphs generated from the stochastic block model. The clustering is fir…
View article: On the inverse problem of source reconstruction from coherence measurements
On the inverse problem of source reconstruction from coherence measurements Open
We consider an inverse source problem for partially coherent light\npropagating in the Fresnel regime. The data is the coherence of the field\nmeasured away from the source. The reconstruction is based on a minimum residue\nformulation, wh…
View article: On the inverse problem of source reconstruction from coherence measurements
On the inverse problem of source reconstruction from coherence measurements Open
We consider an inverse source problem for partially coherent light propagating in the Fresnel regime. The data is the coherence of the field measured away from the source. The reconstruction is based on a minimum residue formulation, which…
View article: Spatial coherence of fields from generalized sources in the Fresnel regime
Spatial coherence of fields from generalized sources in the Fresnel regime Open
Analytic expressions of the spatial coherence of partially coherent fields propagating in the Fresnel regime in all but the simplest of scenarios are largely lacking, and calculation of the Fresnel transform typically entails tedious numer…