Related papers: Brax -- A Differentiable Physics Engine for Large …
In robot control, planning, and learning, there is a need for rigid-body dynamics libraries that are highly performant, easy to use, and compatible with CPUs and accelerators. While existing libraries often excel at either low-latency CPU…
Deep Reinforcement Learning can play a key role in addressing sustainable energy challenges. For instance, many grid systems are heavily congested, highlighting the urgent need to enhance operational efficiency. However, reinforcement…
We introduce JAX MD, a software package for performing differentiable physics simulations with a focus on molecular dynamics. JAX MD includes a number of physics simulation environments, as well as interaction potentials and neural networks…
We propose Pgx, a suite of board game reinforcement learning (RL) environments written in JAX and optimized for GPU/TPU accelerators. By leveraging JAX's auto-vectorization and parallelization over accelerators, Pgx can efficiently scale to…
Federated learning is a machine learning technique that enables training across decentralized data. Recently, federated learning has become an active area of research due to an increased focus on privacy and security. In light of this, a…
We present PixelBrax, a set of continuous control tasks with pixel observations. We combine the Brax physics engine with a pure JAX renderer, allowing reinforcement learning (RL) experiments to run end-to-end on the GPU. PixelBrax can…
Reinforcement learning has been demonstrated to outperform even the best humans in complex domains like video games. However, running reinforcement learning experiments on the required scale for autonomous driving is extremely difficult.…
We introduce Atomistic learned potentials in JAX (apax), a flexible and efficient open source software package for training and inference of machine-learned interatomic potentials. Built on the JAX framework, apax supports GPU acceleration…
The development of reinforcement learning (RL) algorithms has been largely driven by ambitious challenge tasks and benchmarks. Games have dominated RL benchmarks because they present relevant challenges, are inexpensive to run and easy to…
Modal methods for simulating vibrations of strings, membranes, and plates are widely used in acoustics and physically informed audio synthesis. However, traditional implementations, particularly for non-linear models like the von K\'arm\'an…
As Deep Reinforcement Learning (Deep RL) research moves towards solving large-scale worlds, efficient environment simulations become crucial for rapid experimentation. However, most existing environments struggle to scale to high…
CLAX is a JAX-based library that implements classic click models using modern gradient-based optimization. While neural click models have emerged over the past decade, complex click models based on probabilistic graphical models (PGMs) have…
This paper presents the new Deep Reinforcement Learning (DRL) library RL-X and its application to the RoboCup Soccer Simulation 3D League and classic DRL benchmarks. RL-X provides a flexible and easy-to-extend codebase with self-contained…
The development of deep learning software libraries enabled significant progress in the field by allowing users to focus on modeling, while letting the library to take care of the tedious and time-consuming task of optimizing execution for…
Benchmarks are crucial in the development of machine learning algorithms, with available environments significantly influencing reinforcement learning (RL) research. Traditionally, RL environments run on the CPU, which limits their…
We present a review of popular simulation engines and frameworks used in reinforcement learning (RL) research, aiming to guide researchers in selecting tools for creating simulated physical environments for RL and training setups. It…
Brain simulation builds dynamical models to mimic the structure and functions of the brain, while brain-inspired computing (BIC) develops intelligent systems by learning from the structure and functions of the brain. The two fields are…
The scaling of Large Language Models (LLMs) for retrieval-based tasks, particularly in Retrieval Augmented Generation (RAG), faces significant memory constraints, especially when fine-tuning extensive prompt sequences. Current open-source…
The design of environments plays a critical role in shaping the development and evaluation of cooperative multi-agent reinforcement learning (MARL) algorithms. While existing benchmarks highlight critical challenges, they often lack the…
We present a feasibility-seeking approach to neural network training. This mathematical optimization framework is distinct from conventional gradient-based loss minimization and uses projection operators and iterative projection algorithms.…