Related papers: Replay Debugging of Complex Real-Time Systems: Exp…

Runtime verification consists in observing and collecting the execution traces of a system and checking them against a specification, with the objective of raising an error when a trace does not satisfy the specification. We consider…

Machine learning tasks entail the use of complex computational pipelines to reach quantitative and qualitative conclusions. If some of the activities in a pipeline produce erroneous or uninformative outputs, the pipeline may fail or produce…

Deep learning model design, development, and debugging is a process driven by best practices, guidelines, trial-and-error, and the personal experiences of model developers. At multiple stages of this process, performance and internal model…

Temporal repetition counting aims to quantify the repeated action cycles within a video. The majority of existing methods rely on the similarity correlation matrix to characterize the repetitiveness of actions, but their scalability is…

Deep learning systems are prone to catastrophic forgetting when learning from a sequence of tasks, as old data from previous tasks is unavailable when learning a new task. To address this, some methods propose replaying data from previous…

Reconstructing system-level behavior from silicon traces is a critical problem in post-silicon validation of System-on-Chip designs. Current industrial practice in this area is primarily manual, depending on collaborative insights of the…

Background: Deep Deterministic Policy Gradient-based reinforcement learning algorithms utilize Actor-Critic architectures, where both networks are typically trained using identical batches of replayed transitions. However, the learning…

Debugging non-deterministic programs on microcontrollers is notoriously challenging, especially when bugs manifest in unpredictable, input-dependent execution paths. A recent approach, called multiverse debugging, makes it easier to debug…

Reactive synthesis is a paradigm for automatically building correct-by-construction systems that interact with an unknown or adversarial environment. We study how to do reactive synthesis when part of the specification of the system is that…

High performance computing systems have historically been designed to support applications comprised of mostly monolithic, single-job workloads. Pilot systems decouple workload specification, resource selection, and task execution via job…

Large-scale data centers and cloud computing have turned system configuration into a challenging problem. Several widely-publicized outages have been blamed not on software bugs, but on configuration bugs. To cope, thousands of…

Performing diagnosis or exploratory analysis during the training of deep learning models is challenging but often necessary for making a sequence of decisions guided by the incremental observations. Currently available systems for this…

Replay in the brain has been viewed as rehearsal, or, more recently, as sampling from a transition model. Here, we propose a new hypothesis: that replay is able to implement a form of compositional computation where entities are assembled…

We study safety verification for multithreaded programs with recursive parallelism (i.e. unbounded thread creation and recursion) as well as unbounded integer variables. Since the threads in each program configuration are structured in a…

Experience replay is central to off-policy algorithms in deep reinforcement learning (RL), but there remain significant gaps in our understanding. We therefore present a systematic and extensive analysis of experience replay in Q-learning…

Symbolic regression is a powerful system identification technique in industrial scenarios where no prior knowledge on model structure is available. Such scenarios often require specific model properties such as interpretability, robustness,…

The history of learning for control has been an exciting back and forth between two broad classes of algorithms: planning and reinforcement learning. Planning algorithms effectively reason over long horizons, but assume access to a local…

Experience replay enables online reinforcement learning agents to store and reuse the previous experiences of interacting with the environment. In the original method, the experiences are sampled and replayed uniformly at random. A prior…

We propose a general and model-free approach for Reinforcement Learning (RL) on real robotics with sparse rewards. We build upon the Deep Deterministic Policy Gradient (DDPG) algorithm to use demonstrations. Both demonstrations and actual…

The deployment of AI systems in safety-critical domains, such as industrial defect inspection, autonomous driving, and medical diagnosis, is severely hampered by their lack of reliability. A single undetected erroneous prediction can lead…