Related papers: RulePlanner: All-in-One Reinforcement Learner for …

Finding tight bounds on the optimal solution is a critical element of practical solution methods for discrete optimization problems. In the last decade, decision diagrams (DDs) have brought a new perspective on obtaining upper and lower…

Placement is an essential task in modern chip design, aiming at placing millions of circuit modules on a 2D chip canvas. Unlike the human-centric solution, which requires months of intense effort by hardware engineers to produce a layout to…

Architectural floor plan design demands joint reasoning over geometry, semantics, and spatial hierarchy, which remains a major challenge for current AI systems. Although recent diffusion and language models improve visual fidelity, they…

Active localization is the problem of generating robot actions that allow it to maximally disambiguate its pose within a reference map. Traditional approaches to this use an information-theoretic criterion for action selection and…

Dyna-style model-based reinforcement learning contains two phases: model rollouts to generate sample for policy learning and real environment exploration using current policy for dynamics model learning. However, due to the complex…

Computer architecture design space is vast and complex. Tools are needed to explore new ideas and gain insights quickly, with low efforts and at a desired accuracy. We propose Calipers, a criticality-based framework to model key…

Designing a multi-layer optical system with designated optical characteristics is an inverse design problem in which the resulting design is determined by several discrete and continuous parameters. In particular, we consider three design…

Inverse design of photonic integrated circuits (PICs) has traditionally relied on gradientbased optimization. However, this approach is prone to end up in local minima, which results in suboptimal design functionality. As interest in PICs…

Optimal designs are usually model-dependent and likely to be sub-optimal if the postulated model is not correctly specified. In practice, it is common that a researcher has a list of candidate models at hand and a design has to be found…

Model calibration and debiasing are fundamental yet operationally expensive challenges in large-scale recommendation systems. Existing approaches treat them as separate problems requiring distinct infrastructure: post-hoc calibration…

Post-hoc interpretability methods typically attribute a model's behavior to its components, data, or training trajectory in isolation. This leads to explanations that lack a unified view and may miss key interactions. While combining…

Reinforcement learning systems require good representations to work well. For decades practical success in reinforcement learning was limited to small domains. Deep reinforcement learning systems, on the other hand, are scalable, not…

Robotic manipulation is challenging due to discontinuous dynamics, as well as high-dimensional state and action spaces. Data-driven approaches that succeed in manipulation tasks require large amounts of data and expert demonstrations,…

In this paper we design hybrid control policies for hybrid systems whose mathematical models are unknown. Our contributions are threefold. First, we propose a framework for modelling the hybrid control design problem as a single Markov…

This paper aims to examine the potential of using the emerging deep reinforcement learning techniques in flight control. Instead of learning from scratch, we suggest to leverage domain knowledge available in learning to improve learning…

Most deep learning recommendation models operate as black boxes, relying on latent representations that obscure their decision process. This lack of intrinsic interpretability raises concerns in applications that require transparency and…

Model-based reinforcement learning attempts to use an available or learned model to improve the data efficiency of reinforcement learning. This work proposes a one-step lookback approach that jointly learns the deep incremental model and…

The phase-ordering problem of modern compilers has received a lot of attention from the research community over the years, yet remains largely unsolved. Various optimization sequences exposed to the user are manually designed by compiler…

Control policy learning for modular robot locomotion has previously been limited to proprioceptive feedback and flat terrain. This paper develops policies for modular systems with vision traversing more challenging environments. These…

Code reasoning refers to the task of predicting the output of a program given its source code and specific inputs. It can measure the reasoning capability of large language models (LLMs) and also benefit downstream tasks such as code…