Proximal Policy Optimization (PPO) is a popular on-policy reinforcement learning algorithm but is significantly less utilized than off-policy learning algorithms in multi-agent problems. In this work, we investigate Multi-Agent PPO (MAPPO), a multi-agent PPO variant which adopts a centralized value function. Using a 1-GPU desktop, we show that MAPPO achieves performance comparable to the state-of-the-art in three popular multi-agent testbeds: the Particle World environments, Starcraft II Micromanagement Tasks, and the Hanabi Challenge, with minimal hyperparameter tuning and without any domain-specific algorithmic modifications or architectures. In the majority of environments, we find that compared to off-policy baselines, MAPPO achieves better or comparable sample complexity as well as substantially faster running time. Finally, we present 5 factors most influential to MAPPO's practical performance with ablation studies.

A fundamental task for artificial intelligence is learning. Deep Neural Networks have proven to cope perfectly with all learning paradigms, i.e. supervised, unsupervised, and reinforcement learning. Nevertheless, traditional deep learning approaches make use of cloud computing facilities and do not scale well to autonomous agents with low computational resources. Even in the cloud, they suffer from computational and memory limitations, and they cannot be used to model adequately large physical worlds for agents which assume networks with billions of neurons. These issues are addressed in the last few years by the emerging topic of sparse training, which trains sparse networks from scratch. This paper discusses sparse training state-of-the-art, its challenges and limitations while introducing a couple of new theoretical research directions which has the potential of alleviating sparse training limitations to push deep learning scalability well beyond its current boundaries. Nevertheless, the theoretical advancements impact in complex multi-agents settings is discussed from a real-world perspective, using the smart grid case study.

Fox News Flash top headlines are here. Check out what's clicking on Foxnews.com. J.J. Watt has apparently found his team new: the Arizona Cardinals. Watt tweeted a picture of himself working out in a Cardinals shirt, signaling that he will join the team for the 2021 season. Watt agreed to a two-year deal worth $31 million, ESPN reported.

Deep learning has seen a movement away from representing examples with a monolithic hidden state towards a richly structured state. For example, Transformers segment by position, and object-centric architectures decompose images into entities. In all these architectures, interactions between different elements are modeled via pairwise interactions: Transformers make use of self-attention to incorporate information from other positions; object-centric architectures make use of graph neural networks to model interactions among entities. However, pairwise interactions may not achieve global coordination or a coherent, integrated representation that can be used for downstream tasks. In cognitive science, a global workspace architecture has been proposed in which functionally specialized components share information through a common, bandwidth-limited communication channel. We explore the use of such a communication channel in the context of deep learning for modeling the structure of complex environments. The proposed method includes a shared workspace through which communication among different specialist modules takes place but due to limits on the communication bandwidth, specialist modules must compete for access. We show that capacity limitations have a rational basis in that (1) they encourage specialization and compositionality and (2) they facilitate the synchronization of otherwise independent specialists.

We address scaling up equilibrium computation in Mean Field Games (MFGs) using Online Mirror Descent (OMD). We show that continuous-time OMD provably converges to a Nash equilibrium under a natural and well-motivated set of monotonicity assumptions. This theoretical result nicely extends to multi-population games and to settings involving common noise. A thorough experimental investigation on various single and multi-population MFGs shows that OMD outperforms traditional algorithms such as Fictitious Play (FP). We empirically show that OMD scales up and converges significantly faster than FP by solving, for the first time to our knowledge, examples of MFGs with hundreds of billions states. This study establishes the state-of-the-art for learning in large-scale multi-agent and multi-population games.

From March 1 to April 4, 2020, the Illinois Department of Employment Security received 513,173 unemployment claims -- more than the entire number of claims filed in 2019. It was impossible for IDES employees to handle this volume, resulting in many disconnected phone calls and unanswered online queries. Gov. J.B. Pritzker called for increased call center capacity, in large part through the implementation of new technologies to help employees handle the volume of queries. Gov. Pritzker wanted to minimize dropped calls and deliver a response to all online queries so citizens could receive the benefits they needed. This new technology, virtual intelligent agents, alleviated overburdened human agents from having to respond to every inquiry that came in.

Many social sciences such as psychology and economics try to learn the behaviour of complex agents such as humans, organisations and countries. The current statistical methods used for learning this behaviour try to infer generally valid behaviour, but can only learn from one type of study at a time. Furthermore, only data from carefully designed studies can be used, as the phenomenon of interest has to be isolated and confounding factors accounted for. These restrictions limit the robustness and accuracy of insights that can be gained from social/economic systems. Here we present the online platform TreeOfKnowledge which implements a new methodology specifically designed for learning complex behaviours from complex systems: agent-based behaviour learning. With agent-based behaviour learning it is possible to gain more accurate and robust insights as it does not have the restriction of conventional statistics. It learns agent behaviour from many heterogenous datasets and can learn from these datasets even if the phenomenon of interest is not directly observed, but appears deep within complex systems. This new methodology shows how the internet and advances in computational power allow for more accurate and powerful mathematical models.

Human brain has been used as an inspiration for building autonomous agents, but it is not obvious what level of computational description of the brain one should use. This has led to overly opinionated symbolic approaches and overly unstructured connectionist approaches. We propose that using homeostasis as the computational description provides a good compromise. Similar to how physiological homeostasis is the regulation of certain homeostatic variables, cognition can be interpreted as the regulation of certain 'cognitive homeostatic variables'. We present an outline of a Cognitive Homeostatic Agent, built as a hierarchy of physiological and cognitive homeostatic subsystems and describe structures and processes to guide future exploration. We expect this to be a fruitful line of investigation towards building sophisticated artificial agents that can act flexibly in complex environments, and produce behaviors indicating planning, thinking and feelings.

Yoshua Bengio is one of the world's leading experts in artificial intelligence and deep learning. Also known as the father of deep learning, he says that for the world to change for the better with AI, a global shift in how organizations and governments share their research needs to come. In many countries, private companies, government entities, and academic institutions conduct AI research. These places must foster a global culture of open science. These research places the need to rethink how to encourage the development of impactful artificial intelligence.

Traffic congestion is a major challenge in modern urban settings. The industry-wide development of autonomous and automated vehicles (AVs) motivates the question of how can AVs contribute to congestion reduction. Past research has shown that in small scale mixed traffic scenarios with both AVs and human-driven vehicles, a small fraction of AVs executing a controlled multiagent driving policy can mitigate congestion. In this paper, we scale up existing approaches and develop new multiagent driving policies for AVs in scenarios with greater complexity. We start by showing that a congestion metric used by past research is manipulable in open road network scenarios where vehicles dynamically join and leave the road. We then propose using a different metric that is robust to manipulation and reflects open network traffic efficiency. Next, we propose a modular transfer reinforcement learning approach, and use it to scale up a multiagent driving policy to outperform human-like traffic and existing approaches in a simulated realistic scenario, which is an order of magnitude larger than past scenarios (hundreds instead of tens of vehicles). Additionally, our modular transfer learning approach saves up to 80% of the training time in our experiments, by focusing its data collection on key locations in the network. Finally, we show for the first time a distributed multiagent policy that improves congestion over human-driven traffic. The distributed approach is more realistic and practical, as it relies solely on existing sensing and actuation capabilities, and does not require adding new communication infrastructure.