Related papers: Brax -- A Differentiable Physics Engine for Large …

In a landscape of high-performance distributed ML systems, JAX has emerged as a framework of choice. However, JAX's modular design philosophy leaves it without a standardized checkpointing solution. In this paper, we introduce Orbax, a…

We present an open-source library of natively differentiable physics and robotics environments, accompanied by gradient-based control methods and a benchmark-ing suite. The introduced environments allow auto-differentiation through the…

Unsupervised environment design (UED) is a form of automatic curriculum learning for training robust decision-making agents to zero-shot transfer into unseen environments. Such autocurricula have received much interest from the RL…

While large models trained with self-supervised learning on offline datasets have shown remarkable capabilities in text and image domains, achieving the same generalisation for agents that act in sequential decision problems remains an open…

Numerical simulations are ubiquitous in mathematics and computational science. Several industrial and clinical applications entail modeling complex multiphysics systems that evolve over a variety of spatial and temporal scales. This study…

We introduce GRiD: a GPU-accelerated library for computing rigid body dynamics with analytical gradients. GRiD was designed to accelerate the nonlinear trajectory optimization subproblem used in state-of-the-art robotic planning, control,…

OpenReservoirComputing (ORC) is a Python library for reservoir computing (RC) written in JAX (Bradbury et al. 2018) and Equinox (Kidger and Garcia 2021). JAX is a Python library for high-performance numerical computing that enables…

Epithelial tissues dynamically reshape through local mechanical interactions among cells, a process well captured by vertex models. Yet their many tunable parameters make inference and optimization challenging, motivating computational…

Building differentiable simulations of physical processes has recently received an increasing amount of attention. Specifically, some efforts develop differentiable robotic physics engines motivated by the computational benefits of merging…

Mixed-precision training has emerged as an indispensable tool for enhancing the efficiency of neural network training in recent years. Concurrently, JAX has grown in popularity as a versatile machine learning toolbox. However, it currently…

Reinforcement learning (RL) has enabled advances in humanoid robot locomotion, yet most learning frameworks do not account for mechanical intelligence embedded in parallel actuation mechanisms due to limitations in simulator support for…

Inspired by the diversity and depth of XLand and the simplicity and minimalism of MiniGrid, we present XLand-MiniGrid, a suite of tools and grid-world environments for meta-reinforcement learning research. Written in JAX, XLand-MiniGrid is…

Sequential social dilemmas pose a significant challenge in the field of multi-agent reinforcement learning (MARL), requiring environments that accurately reflect the tension between individual and collective interests. Previous benchmarks…

Recent advances in Reinforcement Learning (RL) have led to many exciting applications. These advancements have been driven by improvements in both algorithms and engineering, which have resulted in faster training of RL agents. We present…

Learning-based methods have proven useful at generating complex motions for robots, including humanoids. Reinforcement learning (RL) has been used to learn locomotion policies, some of which leverage a periodic reward formulation. This work…

Accurate economic simulations often require many experimental runs, particularly when combined with reinforcement learning. Unfortunately, training reinforcement learning agents in multi-agent economic environments can be slow. This paper…

We present an implementation of interval analysis and mixed monotone interval reachability analysis as function transforms in Python, fully composable with the computational framework JAX. The resulting toolbox inherits several key features…

We present JaxUED, an open-source library providing minimal dependency implementations of modern Unsupervised Environment Design (UED) algorithms in Jax. JaxUED leverages hardware acceleration to obtain on the order of 100x speedups…

Deep reinforcement learning can generate complex control policies, but requires large amounts of training data to work effectively. Recent work has attempted to address this issue by leveraging differentiable simulators. However, inherent…

Agent-based modeling (ABM) is a principal approach for studying complex systems. By decomposing a system into simpler, interacting agents, agent-based modeling (ABM) allows researchers to observe the emergence of complex phenomena.…