Related papers: AlphaZero-Edu: Democratizing Access to AlphaZero

Need for the efficient processing of neural networks has given rise to the development of hardware accelerators. The increased adoption of specialized hardware has highlighted the need for more agile design flows for hardware-software…

Learning predictive world models is crucial for enhancing the planning capabilities of reinforcement learning (RL) agents. Recently, MuZero-style algorithms, leveraging the value equivalence principle and Monte Carlo Tree Search (MCTS),…

The idea of decision-aware model learning, that models should be accurate where it matters for decision-making, has gained prominence in model-based reinforcement learning. While promising theoretical results have been established, the…

Pioneering dual-encoder pre-training works (e.g., CLIP and ALIGN) have revealed the potential of aligning multi-modal representations with contrastive learning. However, these works require a tremendous amount of data and computational…

AlphaZero-like Monte Carlo Tree Search systems, originally introduced for two-player games, dynamically balance exploration and exploitation using neural network guidance. This combination makes them also suitable for classical search…

The rapid growth of programming education has outpaced traditional assessment tools, leaving faculty with limited means to provide meaningful, scalable feedback. Conventional autograders, while efficient, act as black-box systems that…

We propose a generic algorithmic building block to accelerate training of machine learning models on heterogeneous compute systems. Our scheme allows to efficiently employ compute accelerators such as GPUs and FPGAs for the training of…

Based on the Arduino development platform, Plasduino is an open-source data acquisition framework specifically designed for educational physics experiments. The source code, schematics and documentation are in the public domain under a GPL…

The game of chess is the most widely-studied domain in the history of artificial intelligence. The strongest programs are based on a combination of sophisticated search techniques, domain-specific adaptations, and handcrafted evaluation…

Assistance games are a promising alternative to reinforcement learning from human feedback (RLHF) for training AI assistants. Assistance games resolve key drawbacks of RLHF, such as incentives for deceptive behavior, by explicitly modeling…

Recent developments in Artificial Intelligence techniques have enabled their successful application across a spectrum of commercial and industrial settings. However, these techniques require large volumes of data to be aggregated in a…

The advent of modern cloud services along with the huge volume of data produced on a daily basis, have set the demand for fast and efficient data processing. This demand is common among numerous application domains, such as deep learning,…

Reinforcement Learning is a mature technology, often suggested as a potential route towards Artificial General Intelligence, with the ambitious goal of replicating the wide range of abilities found in natural and artificial intelligence,…

Reinforcement learning is considered to be a strong AI paradigm which can be used to teach machines through interaction with the environment and learning from their mistakes. Despite its perceived utility, it has not yet been successfully…

NVIDIA cuDNN is a low-level library that provides GPU kernels frequently used in deep learning. Specifically, cuDNN implements several equivalent convolution algorithms, whose performance and memory footprint may vary considerably,…

There has been a proliferation of artificial intelligence applications, where model training is key to promising high-quality services for these applications. However, the model training process is both time-intensive and energy-intensive,…

Reinforcement learning (RL) has emerged as an effective paradigm for improving the reasoning capability of vision-language models (VLMs). However, RL-based optimization typically depends on costly high-quality annotations that are difficult…

Large-scale deep learning workloads increasingly suffer from I/O bottlenecks as datasets grow beyond local storage capacities and GPU compute outpaces network and disk latencies. While recent systems optimize data-loading time, they…

The architecture of the neural networks used in Deep Reinforcement Learning programs such as Alpha Zero or Polygames has been shown to have a great impact on the performances of the resulting playing engines. For example the use of residual…

Designing protein nanomaterials of predefined shape and characteristics has the potential to dramatically impact the medical industry. Machine learning (ML) has proven successful in protein design, reducing the need for expensive wet lab…