Model-based reinforcement learning (RL), which finds an optimal policy using an empirical model, has long been recognized as one of the corner stones of RL. It is especially suitable for multi-agent RL (MARL), as it naturally decouples the learning and the planning phases, and avoids the non-stationarity problem when all agents are improving their policies simultaneously using samples. Though intuitive and widely-used, the sample complexity of model-based MARL algorithms has not been fully investigated. In this paper, our goal is to address the fundamental question about its sample complexity. We study arguably the most basic MARL setting: two-player discounted zero-sum Markov games, given only access to a generative model. We show that model-based MARL achieves a sample complexity of $\tilde O(|S||A||B|(1-\gamma)^{-3}\epsilon^{-2})$ for finding the Nash equilibrium (NE) value up to some $\epsilon$ error, and the $\epsilon$-NE policies with a smooth planning oracle, where $\gamma$ is the discount factor, and $S,A,B$ denote the state space, and the action spaces for the two agents. We further show that such a sample bound is minimax-optimal (up to logarithmic factors) if the algorithm is reward-agnostic, where the algorithm queries state transition samples without reward knowledge, by establishing a matching lower bound. This is in contrast to the usual reward-aware setting, with a $\tilde\Omega(|S|(|A|+|B|)(1-\gamma)^{-3}\epsilon^{-2})$ lower bound, where this model-based approach is near-optimal with only a gap on the $|A|,|B|$ dependence. Our results not only demonstrate the sample-efficiency of this basic model-based approach in MARL, but also elaborate on the fundamental tradeoff between its power (easily handling the more challenging reward-agnostic case) and limitation (less adaptive and suboptimal in $|A|,|B|$), particularly arises in the multi-agent context.

AI systems have found a wide range of application areas in financial services. Their involvement in broader and increasingly critical decisions has escalated the need for compliance and effective model governance. Current governance practices have evolved from more traditional financial applications and modeling frameworks. They often struggle with the fundamental differences in AI characteristics such as uncertainty in the assumptions, and the lack of explicit programming. AI model governance frequently involves complex review flows and relies heavily on manual steps. As a result, it faces serious challenges in effectiveness, cost, complexity, and speed. Furthermore, the unprecedented rate of growth in the AI model complexity raises questions on the sustainability of the current practices. This paper focuses on the challenges of AI model governance in the financial services industry. As a part of the outlook, we present a system-level framework towards increased self-regulation for robustness and compliance. This approach aims to enable potential solution opportunities through increased automation and the integration of monitoring, management, and mitigation capabilities. The proposed framework also provides model governance and risk management improved capabilities to manage model risk during deployment.

Open Source Python Deep Learning Library – 2015 published – code is hosted on GitHub – originally a uniform interface for various backend libraries (TensorFlow, Microsoft Cognitive Toolkit, Theano, R, PlaidM) – it focuses on being user-friendly, modular, and extensible, and Fast and easy prototyping of neural networks, – Part of the Tensorflow Core API, but was also continued independently – since version 2.4 Keras refers directly to the implementation of Tensorflow 2 – contains numerous implementations of commonly used neural-network building blocks (layers, activation functions, objectives, optimizers, tools to make working with image and text data)

Collecting and generating quality data sets to train artificial intelligence models needs to be a priority for the department, with some officials arguing it should be a requirement in contracts moving forward. By being proactive about collecting and generating data, the future of AI can be built on quality inputs, Michael Kanaan, director of operations at the Air Force's AI Accelerator at MIT, said Tuesday during the AFCEA DCAI and ML Technology Summit. Other technology officials endorsed the idea of being more aggressive about data collection rather than being "opportunistic" or working on old, lower quality data sets. For instance, the Air Force used quality data to train a machine learning model that turned the boards that officials use to manually track flight times into an automated, intelligent system. The ML system that replaced the "puck boards" ensured pilots got enough hours to maintain mission readiness.

Bad actors use machine learning to break passwords more quickly and build malware that knows how to hide, experts warn. Three cybersecurity experts explained how artificial intelligence and machine learning can be used to evade cybersecurity defenses and make breaches faster and more efficient during a NCSA and Nasdaq cybersecurity summit. Kevin Coleman, the executive director of the National Cyber Security Alliance, hosted the conversation as part of Usable Security: Effecting and Measuring Change in Human Behavior on Tuesday, Oct. 6. Elham Tabassi, chief of staff information technology laboratory, National Institute of Standards and Technology, was one of the panelists in the "Artificial Intelligence and Machine Learning for Cybersecurity: The Good, the Bad, and the Ugly" session.text Attackers can use AI to evade detections, to hide where they can't be found, and automatically adapt to counter measures," Tabassi said.

SCI COMMUN### Politics The U.S. presidential race was upended in the first days of October as President Donald Trump tested positive for the pandemic virus and spent 3 days in the hospital. He was aggressively treated with two experimental medicines—monoclonal antibodies and the repurposed antiviral remdesivir—and a steroid used in severe COVID-19 cases. Trump returned to the White House on 5 October saying people should not fear the disease. But public health specialists voiced astonishment when he re-entered the building maskless, trailed by questions about his medical condition and a lack of information about how staff members would be protected from infection. All that followed a rancorous first debate on 29 September between Trump and Democratic challenger Joe Biden. Trump mocked Biden for having worn a mask at other times, despite evidence that the precaution reduces transmission of the virus. The president also left scientists puzzled when he described as a “disaster” Biden's role in the response to the H1N1 swine flu outbreak in 2009. Then-President Barack Obama, whom Biden served under as vice president, declared it a public health emergency 6 weeks before the World Health Organization declared a pandemic. That flu killed an estimated 12,000 Americans—far fewer than the 210,000 U.S. deaths recorded so far from COVID-19. > “Very few don't have some sort of connection to Big Tech.” > > Doctoral student Mohamed Abdalla , in Wired , about a study he led of faculty members specializing in artificial intelligence at four leading research universities. He found 58% (48 of 83) had received a grant or fellowship from one of 14 large technology companies, which may distort research priorities. ### Conservation High-tech fake turtle eggs can spy on poachers and wildlife trafficking routes. The real eggs are a delicacy in Central America, and illicit trading of them adds to other hazards to the survival of turtle species that are threatened. Researchers slipped 101 decoy eggs with GPS trackers embedded (left) into nests on four Costa Rican beaches. The scientists tracked five eggs to learn where the poachers took them; the farthest ended up 137 kilometers inland, the multinational team reported on 5 October in Current Biology . The researchers did not share this information with authorities, noting ethical concerns; many poachers live in poverty, and in Costa Rica, buying the eggs is not illegal. But, the authors say, the study shows that law enforcement agencies could use the method. ### Public health Coronavirus guidelines issued last week by the U.S. Centers for Disease Control and Prevention (CDC) again stirred controversy and concerns that undue political pressure had influenced some of its decisions. CDC announced that on 31 October it will lift an order barring cruise ships from sailing despite a recommendation by its director, Robert Redfield, to extend the ban until February 2021. The industry shut down in March after severe COVID-19 outbreaks occurred on multiple ships. Last week, CDC also drew fire for its updated guidelines on when colleges should test students and faculty and staff members for the pandemic virus. The agency recommended different frequencies of testing, including just a single, initial one, depending on circumstances such as whether students lived in residences with others who tested positive. Critics said the new guidelines should have recommended more regular testing of asymptomatic individuals. CDC addressed another uproar this week by acknowledging evidence that the virus can travel by air and infect people standing more than 2 meters apart in indoor spaces. The agency was faulted last month after it posted, and then withdrew, a draft suggesting otherwise. ### Infectious diseases An international program to reduce the risk of new zoonotic diseases, allowed to expire by the U.S. government in 2019 but extended until last month, will get a successor. On 30 September, the United States Agency for International Development (USAID) awarded a $100 million grant to help countries in Asia and Africa curb viruses jumping from animals to humans. The 5-year Strategies to Prevent Spillover program will have a different focus from its predecessor, PREDICT, whose termination was criticized by the scientific community: Rather than studying the drivers of spillover, it will seek interventions to reduce viral jumps, a USAID spokesperson says. A key goal is to “help partners at the country level build their expertise and ability to take action,” says veterinarian Deborah Kochevar of Tufts University, which leads a 13-institute consortium that won the grant. ### International affairs Yuri Orlov, the Russian physicist who championed human rights in the Soviet Union before being exiled in 1985, died on 27 September at age 96. Orlov helped organize the Soviet Union's branch of Amnesty International in 1973 and 3 years later co-founded the Moscow Helsinki Group, which monitored Soviet adherence to the civil rights provisions of the 1975 Helsinki Accords between the Soviet Union and the West. In 1977, Orlov was arrested and sentenced to 12 years of hard labor and exile in Siberia. After coming to the United States in a prisoner exchange, Orlov, an expert in particle accelerators, worked at Cornell University. He didn't think much of Russian President Vladimir Putin, writing in 2004 that “Russia is flying backward in time.” ### Governance Japan's new prime minister, Yoshihide Suga, has disrupted the process by which scientists are appointed to serve on the governing body of the country's leading academic society, the Science Council of Japan (SCJ). Researchers are criticizing the move as a threat to academic freedom. SCJ makes policy recommendations, promotes scientific literacy and international cooperation, and represents the interests of more than 800,000 scholars in virtually all academic disciplines. The prime minister customarily ratifies appointees recommended by SCJ for its governing body, the General Assembly. But according to an announcement last week, Suga withheld his blessing from six academics, in a list of 105 put forward, who work in the social sciences, law, and the humanities. All six had criticized legislation adopted by Japan's previous government, in which Suga was chief cabinet secretary. His failure to appoint them violated a law governing SCJ, said Satoshi Ihara, secretary general of the Japan Scientists' Association. ### Policy Mexican scientists this week blasted a move by the national legislature to eliminate 109 trust funds run by public research centers and government institutes, one-third of them devoted to science and technology. The government wants to use the money, some $3 billion in total, for the coronavirus pandemic. The funds support everything from student scholarships and emergency maintenance of equipment to major research projects at dozens of government centers. The money also helps pay for biosecurity and biotechnology research, fighting climate change, and disaster relief. On 6 October, Mexico's Chamber of Deputies approved a bill to terminate the funds, but with “reservations” that require further debate; it is expected to pass in the Senate. The plan is “a brutal blow” and the worst hit to Mexican science in 50 years, says Antonio Lazcano, an evolutionary biologist at the National Autonomous University of Mexico, University City. ### Virology There's been a new case of infection with Alaskapox virus, a recently discovered pathogen that's related to smallpox. Alaska state health authorities reported on 30 September that they had found the virus in a woman from the Fairbanks area with a mild, gray skin lesion on one arm, similar to one seen in 2015 in the first known patient, also a woman from Fairbanks. Human infections with pox-viruses are on the rise, presumably because vaccination against smallpox—which offers some protection against related viruses—was halted after that deadly disease was eradicated 40 years ago. But the Alaska cases are no cause for alarm: There is no evidence the virus can be transmitted between humans—scientists think it came from wild mammals—and the lesions went away by themselves. ### Medicine prize goes to discoverers of virus that destroys the liver The Nobel Prize in Physiology or Medicine was awarded this week for the discovery of the hepatitis C virus, one of the most common causes of liver cancer. The prize went to Harvey Alter of the U.S. National Institutes of Health; Michael Houghton of the University of Alberta, Edmonton; and Charles Rice of Rockefeller University. The hepatitis C virus, transmitted via blood, can cause chronic inflammation of the liver that quietly destroys the organ over decades, ultimately leading to cirrhosis and cancer. The laureates did work over 3 decades to identify the virus and show it was responsible for unexplained cases of hepatitis in people who received blood transfusions. They also developed a test to screen blood donations for the virus, which has nearly eliminated the risk of hepatitis from blood transfusions. Their research ultimately led to a successful treatment for the disease, which has cured millions of people. But about 71 million people worldwide still have chronic hepatitis C, and transmission continues via contaminated medical equipment, sharing drug injection needles, and from infected mothers to newborns during birth. The disease causes few acute symptoms, and testing in many developing countries is limited. ### Black hole hunters receive physics prize The Nobel Prize in Physics has been awarded for pioneering discoveries regarding black holes—self-sustaining gravitational fields so intense that nothing, not even light, can escape. Roger Penrose, a mathematician at the University of Oxford, received half of the $1.1 million prize for his theoretical work, conducted in part with the late Stephen Hawking, that proved a black hole would be stable and thus could be a real astrophysical object and not a mere mathematical curiosity. Astronomers Reinhard Genzel of the Max Planck Institute for Extraterrestrial Physics and Andrea Ghez of the University of California, Los Angeles, share the other half of the prize for deducing the presence of the supermassive black hole that lies in the heart of our Galaxy. Since the 1990s, Genzel and Ghez have led rival research groups that observed stars there, 26,000 light-years from Earth. They found ones orbiting a heavy, unseen object, called Sagittarius A*, at incredible speeds—some of the most convincing evidence for a behemoth black hole, with the mass of millions of Suns. ### Fauci: ‘Skunk at the picnic’ On 23 September, in the relative calm before President Donald Trump's coronavirus infection was revealed, Anthony Fauci relaxed at home after tangling earlier that day with U.S. Senator Rand Paul (R–KY) during a hearing on COVID-19. Fauci still had 200 emails in his inbox to read that night, but the head of the National Institute of Allergy and Infectious Diseases, who also serves on the White House's Coronavirus Task Force, sat down with Science to discuss the pandemic and research on vaccines. (Read the full interview at [scim.ag/FauciOctober][1].) Some excerpts: On his showdown with Paul: “I said to myself, you know, ‘I'm sorry, I'm not gonna disrespect him, but I'm not gonna let him get away with saying things that are cherry-picked data.’” (Paul had suggested that the United States follow Sweden's COVID-19 policies because it had a lower death rate from the disease.) On speaking bluntly at the White House: “I'm walking a fine line of being someone who is not hesitant to tell the president and the vice president what they may not want to hear. There are some people in the White House, who, even when I first started telling it like it was in the task force meetings, they were like, ‘Oh my goodness.’ That's when I got that nickname ‘the skunk at the picnic.’ … I say, ‘I'm sorry, I'm not trying to undermine the president. But there is something that's called reality.’” On the state of the pandemic: “Yes, there are parts of the country that are doing well. But this country is a big forest, and when you have fires in some parts of the forest, the entire forest is at risk.” [1]: http://scim.ag/FauciOctober

As U.S. particle physicists contemplate their future, they find themselves victims of their own surprising success. Seven years ago, the often fractious community hammered out its current research road map and rallied around it. Thanks to that unity—and generous budgets—the Department of Energy (DOE), the field's main U.S. sponsor, has already started on almost every project on the list. So this week, as U.S. particle physicists start to drum up new ideas for the next decade in a yearlong Snowmass process—named for the Colorado ski resort where such planning exercises once took place—they have no single big project to push for (or against). And in some subfields, the next steps seem far less obvious than they were 10 years ago. “We have to be much more open minded about what particle physics and fundamental physics are,” says Young-Kee Kim of the University of Chicago, chair of the American Physical Society's division of particles and fields, which is sponsoring the planning exercise. Ten years ago, the U.S. particle physics community was in disarray. The high-energy frontier had passed to CERN, the European particle physics laboratory near Geneva, where in 2012 the world's biggest atom smasher, the Large Hadron Collider (LHC), blasted out the long-sought Higgs boson, the last piece in particle physicists' standard model. Some physicists wanted the United States to build a huge experiment to fire elusive particles called neutrinos long distances through Earth to study how they “oscillate”—morph from one of their three types to another—as they zip along. Others wanted the country to help push for the next big collider. Those tensions came to a head during the last Snowmass effort in 2013, and the subsequent deliberations of the Particle Physics Project Prioritization Panel (P5), which wrote the road map. U.S. researchers agreed to build the neutrino experiment, but make it bigger and better by inviting international partners. They also decided to continue to participate fully in the LHC, and to pursue a variety of smaller projects at home (see table, below). The next collider would have to wait. Most important, DOE officials warned, the squabbling and backstabbing had to stop. In fact, physicists recall, the 2013 process had an informal motto: “Bickering scientists get nothing.” ![Figure][1] CREDIT: PARTICLE PHYSICS PROJECT PRIORITIZATION PANEL REPORT (2014) Physicists have just started to build the current plan's centerpiece. The Long-Baseline Neutrino Facility (LBNF) at Fermi National Accelerator Laboratory (Fermilab) in Illinois will shoot the particles through 1300 kilometers of rock to the Deep Underground Neutrino Experiment (DUNE) in South Dakota, a detector filled with 40,000 tons of frigid liquid argon. LBNF/DUNE, which should come online in 2026, aims to be the definitive study of neutrino oscillations and whether they differ between neutrinos and antineutrinos, which could help explain how the universe generated more matter than antimatter. “The angst in the neutrino community is a lot lower than it was last time,” says Kate Scholberg, a neutrino physicist at Duke University. “The DUNE program will be going on at least into the 2030s.” However, researchers are already thinking of upgrades to the $2.6 billion experiment, she notes. In other areas, the future looks less certain. The last time around, for example, scientists had a pretty clear path forward in their search for particles of dark matter—the so-far-unidentified stuff that appears to pervade the galaxies and bind them with its gravity. Researchers had built small underground detectors that searched for the signal of weakly interacting massive particles (WIMPs), the leading dark matter candidate, bumping into atomic nuclei. The obvious plan was to expand the detectors to the ton scale. Now, two multi-ton WIMP detectors are under construction. But so far WIMPs haven't shown up, and scaling up that technology further “is probably not going to work very well anymore,” says Marcelle Soares-Santos, a physicist at the University of Michigan, Ann Arbor. “So we need to think a little bit more out of the box.” Researchers are now contemplating a hunt for other types of dark matter particles, using new detectors that exploit quantum mechanical effects to achieve exquisite levels of sensitivity. A perennial question for the field is what the next great particle collider will be. The obvious need is for one that fires electrons into positrons to crank out copious Higgs bosons and study their properties in detail, says Meenakshi Narain, a physicist at Brown University. But possible designs vary. Physicists in Japan are discussing such a Higgs factory in the form of a 30-kilometer-long linear electron-positron collider. Meanwhile, CERN has begun a study of an 80- to 100-kilometer circular collider. China has plans for a similar circular collider. However, Vladimir Shiltsev, an accelerator physicist at Fermilab, says those aren't the only potential options. “The real picture is much murkier.” Snowmass organizers have received at least 16 different proposals for colliders, including one that would smash together muons—heavier, unstable cousins of electrons—and another that would use photons. Snowmass participants should consider all options, Shiltsev says. Joe Lykken, Fermilab's deputy director for research, suggests physicists could even push for DOE to support a massive experiment that has nothing to do with particles: a next-generation detector of gravitational waves, spacetime ripples set off when massive objects such as black holes collide. Their discovery in 2015 by the Laser Interferometer Gravitational-Wave Observatory (LIGO) opened a new window on the universe. LIGO consists of two L-shaped optical instruments with arms 4 kilometers long in Louisiana and Washington; it was built by the National Science Foundation. The next generation of ground-based detectors could be 10 times as big, and might better fit DOE, which specializes in scientific megaprojects, Lykken says. “It starts to sound like the kind of thing that the DOE would be interested in and maybe required for,” he says. During the coming year, Snowmass participants will air the more than 2000 ideas researchers have already proffered in two-page summaries. Then, a new P5 will formulate a new plan. Whatever ideas scientists come up with, to execute their new plan they'll have to maintain the harmony that in recent years has made their planning process an exemplar to other fields. “Being unified is the new norm for us,” quips Jim Siegrist, DOE's associate director for high energy physics. “So we have to continue to keep a lid on divisiveness and that'll be a challenge.” [1]: pending:yes

OSIRIS-REx is ready to get the goods. On 20 October, after several years of patient study of its enigmatic target, NASA's $800 million spacecraft will finally stretch out its robotic arm, swoop to the surface of the near-Earth asteroid Bennu, and sweep up some dust and pebbles. The encounter, 334 million kilometers from Earth, will last about 10 seconds. If it is successful, OSIRIS-REx could steal away with up to 1 kilogram of carbon-rich material from the dawn of the Solar System for return to Earth in 2023. Since OSIRIS-REx (short for Origins, Spectral Interpretation, Resource Identification, Security, Regolith Explorer) arrived in 2018, Bennu has yielded surprises, not all of them welcome. The 500-meter-wide asteroid was not smooth, as expected, but studded with more than 200 large boulders that could upset the sampling maneuver. And every so often, the asteroid ejected coin-size pebbles, probably propelled by meteoroid impacts or solar heating. The boulder hazard, in particular, forced the team to target an area just 16 meters across for sampling, 10 times smaller than planned. “Bennu has not made things easy for us,” says Mike Moreau, the mission's deputy project manager at NASA's Goddard Space Flight Center. ![Figure][1] CREDITS: (GRAPHIC) G. GRULLÓN/ SCIENCE ; (IMAGES, LEFT TO RIGHT) NASA; NASA/GODDARD/UNIVERSITY OF ARIZONA (2) Despite the logistical challenge, the boulders contain a prize: veins of carbonate minerals thicker than your hands, the team reports in one of six studies published today in Science and Science Advances . The minerals, which precipitate out of hot water, popped out of data gathered during a close flyby of light-colored boulders near the target site, called Nightingale. Researchers believe the veins grew in channels of fluid circulating within Bennu's parent body, a larger planetesimal thought to have formed beyond Jupiter's orbit soon after the dawn of the Solar System 4.56 billion years ago, before being smashed apart in the asteroid belt within the last billion years. Heat from the decay of radioactive elements in its interior presumably drove the churning, and the presence of so much carbonate “suggests large-scale fluid flow, possibly over the entire parent body,” says Hannah Kaplan, a planetary scientist at Goddard who led the work. This ancient water world is consistent with the idea that objects like Bennu delivered much of Earth's water when they struck the planet billions of years ago, says Dante Lauretta, the mission's principal investigator and a planetary scientist at the University of Arizona. The veins also suggest watery bodies like Bennu were a cauldron for the organic chemistry that generated the amino acids and other unusual prebiotic compounds found in carbon-rich meteorites ( Science , 14 August, p. [760][2]). OSIRIS-REx won't be sampling the carbonate veins directly: The chamber at the end of its robotic arm is designed to suck up grit smaller than a penny. That's all right, however, because the small pebbles strewn across Nightingale also contain signs of carbonates and other organic molecules, the team reports today. “This gives me a hint that my dream is going to come true,” Lauretta says. “I want to bring back something we've never seen before.” The team picked Nightingale for its abundant pebbles and because the site appears young, probably because an impact exposed it in recent geological time, leaving it largely unaltered by bombarding cosmic rays. But navigating the van-size spacecraft to a safe touchdown still won't be easy; the site is ringed with building-size rocks, including one nicknamed Mount Doom, along with smaller boulders throughout. Observations suggest many of these boulders are porous, almost fluffy, and would crumble if touched. But the team doesn't want to take that chance: Using its cameras to navigate, the spacecraft will automatically abort its approach at an altitude of 5 meters if the site appears hazardous. The entire sampling attempt, lasting 4.5 hours, needs to be autonomous; Bennu is currently five times farther from Earth than Mars, and radio signals take 18 minutes to reach it. After thruster maneuvers bring it to the touch point with Bennu, blasts of nitrogen should push dust and pebbles into the doughnut-shaped collector at the end of the robotic arm. It will be several days before NASA can judge how much was gathered, based on images of the target site and sampling head, and changes in how the spacecraft spins. By the end of the month, managers will decide whether to make a second attempt at a backup site in January 2021. Either way, the spacecraft will leave Bennu next year and head back to Earth. It will arrive in September 2023 and eject the sample capsule, which will parachute to a landing in the Utah desert. [1]: pending:yes [2]: http://www.sciencemag.org/content/369/6505/760

Wilkinson recently had a close call when a shark trailed him, only inches away. Wilkinson recently had a close call when a shark trailed him, only inches away. The surfer had no idea a shark was trailing him. Near Sharpes Beach in Australia, professional surfer Matt Wilkinson was paddling on his board on Wednesday. Unbeknownst to him, a shark quickly surfaced and began stalking the surfing world champion, at one point only inches away.

IBM is no stranger to innovations in space, with a space flight chronology dating all the way back to 1944, when it helped to first design and build the automatic sequence Controlled Calculator for Harvard University which was used by Navy scientists to prepare ballistic tables. Almost 76 years later, IBM looks to be ready to join the space race with its latest foray into artificial intelligence (AI). According to the latest announcements from Big Blue, two new open source AI projects will look to take advantage of space technology in a bid to solve technical challenges around cube satellite communication and the growing problem of space junk. In correlation with the announcement, IBM's Space Tech Hub Team, led by engineer and space tech CTO, Naeem Altaf, unveiled the two open source projects named KubeSat and Space Situational Awareness (SSA) system. IBM's newly open sourced project KubeSat is a cognitive autonomous framework that can be used to create and control satellite swarms and support additional software they need to perform specific tasks, while also enabling the simulation and optimization of multi-satellite communications.