Multi-agent reinforcement learning (MARL) provides a framework for problems involving multiple interacting agents. Despite apparent similarity to the single-agent case, multi-agent problems are often harder to train and analyze theoretically. In this work, we propose MA-Trace, a new on-policy actor-critic algorithm, which extends V-Trace to the MARL setting. The key advantage of our algorithm is its high scalability in a multi-worker setting. To this end, MA-Trace utilizes importance sampling as an off-policy correction method, which allows distributing the computations with no impact on the quality of training. Furthermore, our algorithm is theoretically grounded - we prove a fixed-point theorem that guarantees convergence. We evaluate the algorithm extensively on the StarCraft Multi-Agent Challenge, a standard benchmark for multi-agent algorithms. MA-Trace achieves high performance on all its tasks and exceeds state-of-the-art results on some of them.

A backdoor deep learning (DL) model behaves normally upon clean inputs but misbehaves upon trigger inputs as the backdoor attacker desires, posing severe consequences to DL model deployments. State-of-the-art defenses are either limited to specific backdoor attacks (source-agnostic attacks) or non-user-friendly in that machine learning (ML) expertise or expensive computing resources are required. This work observes that all existing backdoor attacks have an inevitable intrinsic weakness, non-transferability, that is, a trigger input hijacks a backdoored model but cannot be effective to another model that has not been implanted with the same backdoor. With this key observation, we propose non-transferability enabled backdoor detection (NTD) to identify trigger inputs for a model-under-test (MUT) during run-time.Specifically, NTD allows a potentially backdoored MUT to predict a class for an input. In the meantime, NTD leverages a feature extractor (FE) to extract feature vectors for the input and a group of samples randomly picked from its predicted class, and then compares similarity between the input and the samples in the FE's latent space. If the similarity is low, the input is an adversarial trigger input; otherwise, benign. The FE is a free pre-trained model privately reserved from open platforms. As the FE and MUT are from different sources, the attacker is very unlikely to insert the same backdoor into both of them. Because of non-transferability, a trigger effect that does work on the MUT cannot be transferred to the FE, making NTD effective against different types of backdoor attacks. We evaluate NTD on three popular customized tasks such as face recognition, traffic sign recognition and general animal classification, results of which affirm that NDT has high effectiveness (low false acceptance rate) and usability (low false rejection rate) with low detection latency.

This paper considers cooperative Multi-Agent Reinforcement Learning, focusing on emergent communication in settings where multiple pairs of independent learners interact at varying frequencies. In this context, multiple distinct and incompatible languages can emerge. When an agent encounters a speaker of an alternative language, there is a requirement for a period of adaptation before they can efficiently converse. This adaptation results in the emergence of a new language and the forgetting of the previous language. In principle, this is an example of the Catastrophic Forgetting problem which can be mitigated by enabling the agents to learn and maintain multiple languages. We take inspiration from the Continual Learning literature and equip our agents with multi-headed neural networks which enable our agents to be multi-lingual. Our method is empirically validated within a referential MNIST based communication game and is shown to be able to maintain multiple languages where existing approaches cannot.

Hierarchical text classification (HTC) to a taxonomy is essential for various real applications butchallenging since HTC models often need to process a large volume of data that are severelyimbalanced and have hierarchy dependencies. Existing local and global approaches use deep learningto improve HTC by reducing the time complexity and incorporating the hierarchy dependencies.However, it is difficult to satisfy both conditions in a single HTC model. This paper proposes ahierarchy decoder (HiDEC) that uses recursive hierarchy decoding based on an encoder-decoderarchitecture. The key idea of the HiDEC involves decoding a context matrix into a sub-hierarchysequence using recursive hierarchy decoding, while staying aware of hierarchical dependenciesand level information. The HiDEC is a unified model that incorporates the benefits of existingapproaches, thereby alleviating the aforementioned difficulties without any trade-off. In addition, itcan be applied to both single- and multi-label classification with a minor modification. The superiorityof the proposed model was verified on two benchmark datasets (WOS-46985 and RCV1) with anexplanation of the reasons for its success

Estimating the 3D structure of the drivable surface and surrounding environment is a crucial task for assisted and autonomous driving. It is commonly solved either by using expensive 3D sensors such as LiDAR or directly predicting the depth of points via deep learning. Instead of following existing methodologies, we propose Road Planar Parallax Attention Network (RPANet), a new deep neural network for 3D sensing from monocular image sequences based on planar parallax, which takes full advantage of the commonly seen road plane geometry in driving scenes. RPANet takes a pair of images aligned by the homography of the road plane as input and outputs a $\gamma$ map for 3D reconstruction. Beyond estimating the depth or height, the $\gamma$ map has a potential to construct a two-dimensional transformation between two consecutive frames while can be easily derived to depth or height. By warping the consecutive frames using the road plane as a reference, the 3D structure can be estimated from the planar parallax and the residual image displacements. Furthermore, to make the network better perceive the displacements caused by planar parallax, we introduce a novel cross-attention module. We sample data from the Waymo Open Dataset and construct data related to planar parallax. Comprehensive experiments are conducted on the sampled dataset to demonstrate the 3D reconstruction accuracy of our approach in challenging scenarios.

Efficient exploration in deep cooperative multi-agent reinforcement learning (MARL) still remains challenging in complex coordination problems. In this paper, we introduce a novel Episodic Multi-agent reinforcement learning with Curiosity-driven exploration, called EMC. We leverage an insight of popular factorized MARL algorithms that the "induced" individual Q-values, i.e., the individual utility functions used for local execution, are the embeddings of local action-observation histories, and can capture the interaction between agents due to reward backpropagation during centralized training. Therefore, we use prediction errors of individual Q-values as intrinsic rewards for coordinated exploration and utilize episodic memory to exploit explored informative experience to boost policy training. As the dynamics of an agent's individual Q-value function captures the novelty of states and the influence from other agents, our intrinsic reward can induce coordinated exploration to new or promising states. We illustrate the advantages of our method by didactic examples, and demonstrate its significant outperformance over state-of-the-art MARL baselines on challenging tasks in the StarCraft II micromanagement benchmark.

Experts across multiple states and regions are working on cutting edge science like'call recognition' software to help the shy and elusive Eastern Bristlebird recover the devastating Black Summer bushfires. The state-of-the-art deep learning AI pattern recognition tool is one of eight new recovery projects that have received funding through the Morrison Government's multiregional species coordinator. Minister for the Environment Sussan Ley said the projects will cover a range of recovery actions including the use of scientific surveys to record sightings of the birds to improve understanding of subpopulations and habitat connectivity. "Eastern Bristlebirds are a very secretive bird but can be easily recognised by their melodic song and alarm-call, which is why we are developing new listening tools to support the identification and recovery of this endangered species," Minister Ley said. "By creating a tool that automatically and accurately detects the bird's calls from remote field recordings, and updating radio-transmitter attachment methods, we will be able to track remaining and translocated populations to support their recovery in the future. "We will also be using highly-skilled volunteer scientists to collect data that will inform the future recovery actions we need to take to support the recovery of the Bristlebird across its entire range." Other projects for the Eastern Bristlebird will focus on enhancing recovery through habitat restoration, health and disease research, and support for the establishment of a new genetically viable population in Victoria as a safety net in case of extreme weather events or the spread of disease. "One of the key learnings from the Black Summer bushfires was a need for coordinated on-ground action, monitoring and research, across the entire range of a species, to support its recovery," Minister Ley added. "That is why the Australian Government's $200 million investment in bushfire recovery for wildlife and their habitats is seeing states, territories and stakeholders continuing to work together to support the recovery of ecosystems over a year on from the devastating bushfires.

Two years later, the country could be facing another dangerous fire season. However, a University of South Australia PhD candidate, Liang Zhao, has devised a way to use satellites orbiting above Australia to detect very small fires before they become problematic. Zhao is collecting smoke imagery from multiple satellites and then designing and training artificial intelligence (AI) models to recognise small outbreaks, to prevent a repeat of the 2020 summer. Zhao's algorithm will use satellites to improve fire detection, even from 30,000 kilometres away. "The problem with satellites is that those with high spatial resolution, focusing on small areas, tend to have low temporal resolution, taking much longer to capture images for the same location," Zhao said.

A team of researchers from the Faculty of Medicine, Nursing and Health Sciences (MNHS) Department of Infectious Diseases, the Faculty of Information Technology (IT) and The Alfred's Department of Infectious Diseases have been awarded $3.4M from the Medical Research Future Fund (MRFF) for the SuperbugAi Flagship project. With the focus on superbugs during World Antimicrobial Resistance Awareness Week (November 18-24), the innovative project will integrate genomics, electronic healthcare data and artificial intelligence (AI) technologies to address antimicrobial resistance in the healthcare system. The research, which will be mainly based at The Alfred, will also create a tracking and response system which will lead to earlier detection of superbugs, personalised treatment for patients and prevention of outbreaks. SuberbugAi has the potential to save patient lives, prevent superbug spread, and improve healthcare quality, resource use and costs. Lead researcher, Professor Anton Peleg is one of The Alfred's leading physician-scientists and is internationally recognised for his work in antimicrobial resistance.

Computational thinking, a K–12 education movement begun in 2006, has defined a curriculum to teach basic computing in pre-college schools. It has been dramatically more successful than prior computer literacy or fluency movements at convincing K–12 school teachers and boards to adopt a computer curriculum. Learning problem-solving with algorithms is seen widely as valuable for students. Hundreds of CT initiatives have blossomed around the world. By 2010, the movement settled on a definition of CT that can be paraphrased as "Designing computations that get computers to do jobs for us."