arXiv subjects

Nantas Nardelli

Publications and source records attributed to Nantas Nardelli.

At least 19 recordsLinked to original sources

arXiv2025

Analysis of Preheat Propagation in MagLIF-like Plasmas

The preheating and pre-magnetization of fusion fuel are key features in Magnetized Liner Inertial Fusion (MagLIF) configurations. Typically, the energy of the preheat laser is deposited in a central region of the fuel and propagates outward, generating magneto-hydrodynamic structures that impact the fuel mass distribution and magnetic flux compression during the subsequent implosion. We present a theoretical analysis of preheat propagation in a magnetized plasma under conditions typical for MagLIF. The analysis is based on the acoustic time scale for the propagation of pressure disturbances being much shorter than the conductive time scale for heat diffusion. In this regime, the preheat-driven expansion induces the stratification of the fuel and magnetic field, which accumulate in a dense outer shelf bounded by the leading shock. We derive self-similar solutions of the model that describe the hydrodynamic profiles of the expansion, and evaluate the evolution of the magnetic field in this configuration. These solutions are supported by FLASH simulations of preheat propagation. Our analysis shows that, asymptotically in time, the regions where the magnetization of the fuel is significant tend to become localized at the interface separating the outer shelf from the inner hot core. We assess the implications of this stratification on the magnetic flux conservation and performance of fully integrated MagLIF FLASH simulations.

physics.plasm-ph↗

arXiv2025

Affordable, manageable, practical, and scalable (AMPS) high-yield and high-gain inertial fusion

High-yield inertial fusion offers a transformative path to affordable clean firm power and advanced defense capabilities. Recent milestones at large facilities, particularly the National Ignition Facility (NIF), have demonstrated the feasibility of ignition but highlight the need for approaches that can deliver large amounts of energy to fusion targets at much higher efficiency and lower cost. We propose that pulser-driven inertial fusion energy (IFE), which uses high-current pulsed-power technology to compress targets to thermonuclear conditions, can achieve this goal. In this paper, we detail the physics basis for pulser IFE, focusing on magnetized liner inertial fusion (MagLIF), where cylindrical metal liners compress DT fuel under strong magnetic fields and pre-heat. We discuss how the low implosion velocities, direct-drive efficiency, and scalable pulser architecture can achieve ignition-level conditions at low capital cost. Our multi-dimensional simulations, benchmarked against experiments at the Z facility, show that scaling from 20 MA to 50-60 MA of current enables net facility gain. We then introduce our Demonstration System (DS), a pulsed-power driver designed to deliver more than 60 MA and store approximately 80 MJ of energy. The DS is designed to achieve a 1000x increase in effective performance compared to the NIF, delivering approximately 100x greater facility-level energy gain -- and importantly, achieving net facility gain, or Qf>1 -- at just 1/10 the capital cost. We also examine the engineering requirements for repetitive operation, target fabrication, and chamber maintenance, highlighting a practical roadmap to commercial power plants.

physics.plasm-ph↗

arXiv2025

Validation of FLASH for magnetically driven inertial confinement fusion target design

FLASH is a widely available radiation magnetohydrodynamics code used for astrophysics, laboratory plasma science, high energy density physics, and inertial confinement fusion. Increasing interest in magnetically driven inertial confinement fusion (ICF), including Pacific Fusion's development of a 60 MA Demonstration System designed to achieve facility gain, motivates the improvement and validation of FLASH for modeling magnetically driven ICF concepts, such as MagLIF, at ignition scale. Here we present a collection of six validation benchmarks from experiments at the Z Pulsed Power Facility and theoretical and simulation studies of scaling MagLIF to high currents. The benchmarks range in complexity from focused experiments of linear hydrodynamic instabilities to fully integrated MagLIF fusion experiments. With the latest addition of physics capabilities, FLASH now obtains good agreement with the experimental data, theoretical results, and leading ICF target design simulation code results across all six benchmarks. These results establish confidence in FLASH as a useful tool for designing magnetically driven ICF targets on facilities like Z and Pacific Fusion's upcoming Demonstration System.

physics.plasm-ph↗

arXiv2024

Counterfactual Multi-Agent Policy Gradients

Cooperative multi-agent systems can be naturally used to model many real world problems, such as network packet routing and the coordination of autonomous vehicles. There is a great need for new reinforcement learning methods that can efficiently learn decentralised policies for such systems. To this end, we propose a new multi-agent actor-critic method called counterfactual multi-agent (COMA) policy gradients. COMA uses a centralised critic to estimate the Q-function and decentralised actors to optimise the agents' policies. In addition, to address the challenges of multi-agent credit assignment, it uses a counterfactual baseline that marginalises out a single agent's action, while keeping the other agents' actions fixed. COMA also uses a critic representation that allows the counterfactual baseline to be computed efficiently in a single forward pass. We evaluate COMA in the testbed of StarCraft unit micromanagement, using a decentralised variant with significant partial observability. COMA significantly improves average performance over other multi-agent actor-critic methods in this setting, and the best performing agents are competitive with state-of-the-art centralised controllers that get access to the full state.

cs.AI↗

arXiv2023

Can Reinforcement Learning support policy makers? A preliminary study with Integrated Assessment Models

Governments around the world aspire to ground decision-making on evidence. Many of the foundations of policy making - e.g. sensing patterns that relate to societal needs, developing evidence-based programs, forecasting potential outcomes of policy changes, and monitoring effectiveness of policy programs - have the potential to benefit from the use of large-scale datasets or simulations together with intelligent algorithms. These could, if designed and deployed in a way that is well grounded on scientific evidence, enable a more comprehensive, faster, and rigorous approach to policy making. Integrated Assessment Models (IAM) is a broad umbrella covering scientific models that attempt to link main features of society and economy with the biosphere into one modelling framework. At present, these systems are probed by policy makers and advisory groups in a hypothesis-driven manner. In this paper, we empirically demonstrate that modern Reinforcement Learning can be used to probe IAMs and explore the space of solutions in a more principled manner. While the implication of our results are modest since the environment is simplistic, we believe that this is a stepping stone towards more ambitious use cases, which could allow for effective exploration of policies and understanding of their consequences and limitations.

cs.AI↗

arXiv2022

Insights From the NeurIPS 2021 NetHack Challenge

In this report, we summarize the takeaways from the first NeurIPS 2021 NetHack Challenge. Participants were tasked with developing a program or agent that can win (i.e., 'ascend' in) the popular dungeon-crawler game of NetHack by interacting with the NetHack Learning Environment (NLE), a scalable, procedurally generated, and challenging Gym environment for reinforcement learning (RL). The challenge showcased community-driven progress in AI with many diverse approaches significantly beating the previously best results on NetHack. Furthermore, it served as a direct comparison between neural (e.g., deep RL) and symbolic AI, as well as hybrid systems, demonstrating that on NetHack symbolic bots currently outperform deep RL by a large margin. Lastly, no agent got close to winning the game, illustrating NetHack's suitability as a long-term benchmark for AI research.

cs.LG↗

arXiv2021

MVFST-RL: An Asynchronous RL Framework for Congestion Control with Delayed Actions

Effective network congestion control strategies are key to keeping the Internet (or any large computer network) operational. Network congestion control has been dominated by hand-crafted heuristics for decades. Recently, ReinforcementLearning (RL) has emerged as an alternative to automatically optimize such control strategies. Research so far has primarily considered RL interfaces which block the sender while an agent considers its next action. This is largely an artifact of building on top of frameworks designed for RL in games (e.g. OpenAI Gym). However, this does not translate to real-world networking environments, where a network sender waiting on a policy without sending data leads to under-utilization of bandwidth. We instead propose to formulate congestion control with an asynchronous RL agent that handles delayed actions. We present MVFST-RL, a scalable framework for congestion control in the QUIC transport protocol that leverages state-of-the-art in asynchronous RL training with off-policy correction. We analyze modeling improvements to mitigate the deviation from Markovian dynamics, and evaluate our method on emulated networks from the Pantheon benchmark platform. The source code is publicly available at https://github.com/facebookresearch/mvfst-rl.

cs.LG↗

arXiv2020

The NetHack Learning Environment

Progress in Reinforcement Learning (RL) algorithms goes hand-in-hand with the development of challenging environments that test the limits of current methods. While existing RL environments are either sufficiently complex or based on fast simulation, they are rarely both. Here, we present the NetHack Learning Environment (NLE), a scalable, procedurally generated, stochastic, rich, and challenging environment for RL research based on the popular single-player terminal-based roguelike game, NetHack. We argue that NetHack is sufficiently complex to drive long-term research on problems such as exploration, planning, skill acquisition, and language-conditioned RL, while dramatically reducing the computational resources required to gather a large amount of experience. We compare NLE and its task suite to existing alternatives, and discuss why it is an ideal medium for testing the robustness and systematic generalization of RL agents. We demonstrate empirical success for early stages of the game using a distributed Deep RL baseline and Random Network Distillation exploration, alongside qualitative analysis of various agents trained in the environment. NLE is open source at https://github.com/facebookresearch/nle.

cs.LG↗

arXiv2020

WordCraft: An Environment for Benchmarking Commonsense Agents

The ability to quickly solve a wide range of real-world tasks requires a commonsense understanding of the world. Yet, how to best extract such knowledge from natural language corpora and integrate it with reinforcement learning (RL) agents remains an open challenge. This is partly due to the lack of lightweight simulation environments that sufficiently reflect the semantics of the real world and provide knowledge sources grounded with respect to observations in an RL environment. To better enable research on agents making use of commonsense knowledge, we propose WordCraft, an RL environment based on Little Alchemy 2. This lightweight environment is fast to run and built upon entities and relations inspired by real-world semantics. We evaluate several representation learning methods on this new benchmark and propose a new method for integrating knowledge graphs with an RL agent.

cs.AI↗

arXiv2020

Lessons from reinforcement learning for biological representations of space

Neuroscientists postulate 3D representations in the brain in a variety of different coordinate frames (e.g. 'head-centred', 'hand-centred' and 'world-based'). Recent advances in reinforcement learning demonstrate a quite different approach that may provide a more promising model for biological representations underlying spatial perception and navigation. In this paper, we focus on reinforcement learning methods that reward an agent for arriving at a target image without any attempt to build up a 3D 'map'. We test the ability of this type of representation to support geometrically consistent spatial tasks such as interpolating between learned locations using decoding of feature vectors. We introduce a hand-crafted representation that has, by design, a high degree of geometric consistency and demonstrate that, in this case, information about the persistence of features as the camera translates (e.g. distant features persist) can improve performance on the geometric tasks. These examples avoid Cartesian (in this case, 2D) representations of space. Non-Cartesian, learned representations provide an important stimulus in neuroscience to the search for alternatives to a 'cognitive map'.

q-bio.NC↗

arXiv2020

Multitask Soft Option Learning

We present Multitask Soft Option Learning(MSOL), a hierarchical multitask framework based on Planning as Inference. MSOL extends the concept of options, using separate variational posteriors for each task, regularized by a shared prior. This ''soft'' version of options avoids several instabilities during training in a multitask setting, and provides a natural way to learn both intra-option policies and their terminations. Furthermore, it allows fine-tuning of options for new tasks without forgetting their learned policies, leading to faster training without reducing the expressiveness of the hierarchical policy. We demonstrate empirically that MSOL significantly outperforms both hierarchical and flat transfer-learning baselines.

cs.LG↗

arXiv2020

Simulation-Based Inference for Global Health Decisions

The COVID-19 pandemic has highlighted the importance of in-silico epidemiological modelling in predicting the dynamics of infectious diseases to inform health policy and decision makers about suitable prevention and containment strategies. Work in this setting involves solving challenging inference and control problems in individual-based models of ever increasing complexity. Here we discuss recent breakthroughs in machine learning, specifically in simulation-based inference, and explore its potential as a novel venue for model calibration to support the design and evaluation of public health interventions. To further stimulate research, we are developing software interfaces that turn two cornerstone COVID-19 and malaria epidemiology models COVID-sim, (https://github.com/mrc-ide/covid-sim/) and OpenMalaria (https://github.com/SwissTPH/openmalaria) into probabilistic programs, enabling efficient interpretable Bayesian inference within those simulators.

cs.LG↗

arXiv2019

The StarCraft Multi-Agent Challenge

In the last few years, deep multi-agent reinforcement learning (RL) has become a highly active area of research. A particularly challenging class of problems in this area is partially observable, cooperative, multi-agent learning, in which teams of agents must learn to coordinate their behaviour while conditioning only on their private observations. This is an attractive research area since such problems are relevant to a large number of real-world systems and are also more amenable to evaluation than general-sum problems. Standardised environments such as the ALE and MuJoCo have allowed single-agent RL to move beyond toy domains, such as grid worlds. However, there is no comparable benchmark for cooperative multi-agent RL. As a result, most papers in this field use one-off toy problems, making it difficult to measure real progress. In this paper, we propose the StarCraft Multi-Agent Challenge (SMAC) as a benchmark problem to fill this gap. SMAC is based on the popular real-time strategy game StarCraft II and focuses on micromanagement challenges where each unit is controlled by an independent agent that must act based on local observations. We offer a diverse set of challenge maps and recommendations for best practices in benchmarking and evaluations. We also open-source a deep multi-agent RL learning framework including state-of-the-art algorithms. We believe that SMAC can provide a standard benchmark environment for years to come. Videos of our best agents for several SMAC scenarios are available at: https://youtu.be/VZ7zmQ_obZ0.

cs.LG↗

arXiv2019

TorchBeast: A PyTorch Platform for Distributed RL

TorchBeast is a platform for reinforcement learning (RL) research in PyTorch. It implements a version of the popular IMPALA algorithm for fast, asynchronous, parallel training of RL agents. Additionally, TorchBeast has simplicity as an explicit design goal: We provide both a pure-Python implementation ("MonoBeast") as well as a multi-machine high-performance version ("PolyBeast"). In the latter, parts of the implementation are written in C++, but all parts pertaining to machine learning are kept in simple Python using PyTorch, with the environments provided using the OpenAI Gym interface. This enables researchers to conduct scalable RL research using TorchBeast without any programming knowledge beyond Python and PyTorch. In this paper, we describe the TorchBeast design principles and implementation and demonstrate that it performs on-par with IMPALA on Atari. TorchBeast is released as an open-source package under the Apache 2.0 license and is available at \url{https://github.com/facebookresearch/torchbeast}.

cs.LG↗

arXiv2019

A Survey of Reinforcement Learning Informed by Natural Language

To be successful in real-world tasks, Reinforcement Learning (RL) needs to exploit the compositional, relational, and hierarchical structure of the world, and learn to transfer it to the task at hand. Recent advances in representation learning for language make it possible to build models that acquire world knowledge from text corpora and integrate this knowledge into downstream decision making problems. We thus argue that the time is right to investigate a tight integration of natural language understanding into RL in particular. We survey the state of the field, including work on instruction following, text games, and learning from textual domain knowledge. Finally, we call for the development of new environments as well as further investigation into the potential uses of recent Natural Language Processing (NLP) techniques for such tasks.

cs.LG↗

arXiv2019

Value Propagation Networks

We present Value Propagation (VProp), a set of parameter-efficient differentiable planning modules built on Value Iteration which can successfully be trained using reinforcement learning to solve unseen tasks, has the capability to generalize to larger map sizes, and can learn to navigate in dynamic environments. We show that the modules enable learning to plan when the environment also includes stochastic elements, providing a cost-efficient learning system to build low-level size-invariant planners for a variety of interactive navigation problems. We evaluate on static and dynamic configurations of MazeBase grid-worlds, with randomly generated environments of several different sizes, and on a StarCraft navigation scenario, with more complex dynamics, and pixels as input.

cs.AI↗

arXiv2018

Stabilising Experience Replay for Deep Multi-Agent Reinforcement Learning

Many real-world problems, such as network packet routing and urban traffic control, are naturally modeled as multi-agent reinforcement learning (RL) problems. However, existing multi-agent RL methods typically scale poorly in the problem size. Therefore, a key challenge is to translate the success of deep learning on single-agent RL to the multi-agent setting. A major stumbling block is that independent Q-learning, the most popular multi-agent RL method, introduces nonstationarity that makes it incompatible with the experience replay memory on which deep Q-learning relies. This paper proposes two methods that address this problem: 1) using a multi-agent variant of importance sampling to naturally decay obsolete data and 2) conditioning each agent's value function on a fingerprint that disambiguates the age of the data sampled from the replay memory. Results on a challenging decentralised variant of StarCraft unit micromanagement confirm that these methods enable the successful combination of experience replay with multi-agent RL.

cs.AI↗

arXiv2016

Playing Doom with SLAM-Augmented Deep Reinforcement Learning

A number of recent approaches to policy learning in 2D game domains have been successful going directly from raw input images to actions. However when employed in complex 3D environments, they typically suffer from challenges related to partial observability, combinatorial exploration spaces, path planning, and a scarcity of rewarding scenarios. Inspired from prior work in human cognition that indicates how humans employ a variety of semantic concepts and abstractions (object categories, localisation, etc.) to reason about the world, we build an agent-model that incorporates such abstractions into its policy-learning framework. We augment the raw image input to a Deep Q-Learning Network (DQN), by adding details of objects and structural elements encountered, along with the agent's localisation. The different components are automatically extracted and composed into a topological representation using on-the-fly object detection and 3D-scene reconstruction.We evaluate the efficacy of our approach in Doom, a 3D first-person combat game that exhibits a number of challenges discussed, and show that our augmented framework consistently learns better, more effective policies.

cs.AI↗