There are abstract and other pure sciences which have applications in conjunction with some areas to NLP. Some examples of this include the Whale Optimization Techniques, The Particle Swarm Optimization, Genetic Algorithms. All these are however included in optimization techniques but the key science behind these are either in biology or physical sciences. These techniques are for instance used to optimise the parameters of a deep learning model in say a recommender system or a fake news detection NLP task.

The DONUts platform may look like a collection of bronze-colored, futuristic coffee cups, but everything becomes clearer as they begin to move. The group of modular robots dance in a well-choreographed symphony as magnets turn on and off allowing the modules to pull or push their neighbors. Using these simple interactions, the modular robots can achieve complex tasks such as energy harvesting [1]. Nialah Wilson is one of the key roboticists who helped bring these modular robots to life. Taking advantage of the right message, passed at the right time, is also one of the things that led to Nialah's career in robotics.

Computational metacognition represents a cognitive systems perspective on high-order reasoning in integrated artificial systems that seeks to leverage ideas from human metacognition and from metareasoning approaches in artificial intelligence. The key characteristic is to declaratively represent and then monitor traces of cognitive activity in an intelligent system in order to manage the performance of cognition itself. Improvements in cognition then lead to improvements in behavior and thus performance. We illustrate these concepts with an agent implementation in a cognitive architecture called MIDCA and show the value of metacognition in problem-solving. The results illustrate how computational metacognition improves performance by changing cognition through meta-level goal operations and learning.

An efficient and reliable multi-agent decision-making system is highly demanded for the safe and efficient operation of connected autonomous vehicles in intelligent transportation systems. Current researches mainly focus on the Deep Reinforcement Learning (DRL) methods. However, utilizing DRL methods in interactive traffic scenarios is hard to represent the mutual effects between different vehicles and model the dynamic traffic environments due to the lack of interactive information in the representation of the environments, which results in low accuracy of cooperative decisions generation. To tackle these difficulties, this research proposes a framework to enable different Graph Reinforcement Learning (GRL) methods for decision-making, and compares their performance in interactive driving scenarios. GRL methods combinate the Graph Neural Network (GNN) and DRL to achieve the better decisions generation in interactive scenarios of autonomous vehicles, where the features of interactive scenarios are extracted by the GNN, and cooperative behaviors are generated by DRL framework. Several GRL approaches are summarized and implemented in the proposed framework. To evaluate the performance of the proposed GRL methods, an interactive driving scenarios on highway with two ramps is constructed, and simulated experiment in the SUMO platform is carried out to evaluate the performance of different GRL approaches. Finally, results are analyzed in multiple perspectives and dimensions to compare the characteristic of different GRL approaches in intelligent transportation scenarios. Results show that the implementation of GNN can well represents the interaction between vehicles, and the combination of GNN and DRL is able to improve the performance of the generation of lane-change behaviors. The source code of our work can be found at https://github.com/Jacklinkk/TorchGRL.

The paper considers independent reinforcement learning (IRL) for multi-agent decision-making process in the paradigm of federated learning (FL). We show that FL can clearly improve the policy performance of IRL in terms of training efficiency and stability. However, since the policy parameters are trained locally and aggregated iteratively through a central server in FL, frequent information exchange incurs a large amount of communication overheads. To reach a good balance between improving the model's convergence performance and reducing the required communication and computation overheads, this paper proposes a system utility function and develops a consensus-based optimization scheme on top of the periodic averaging method, which introduces the consensus algorithm into FL for the exchange of a model's local gradients. This paper also provides novel convergence guarantees for the developed method, and demonstrates its superior effectiveness and efficiency in improving the system utility value through theoretical analyses and numerical simulation results.

An unaddressed challenge in human-AI coordination is to enable AI agents to exploit the semantic relationships between the features of actions and the features of observations. Humans take advantage of these relationships in highly intuitive ways. For instance, in the absence of a shared language, we might point to the object we desire or hold up our fingers to indicate how many objects we want. To address this challenge, we investigate the effect of network architecture on the propensity of learning algorithms to exploit these semantic relationships. Across a procedurally generated coordination task, we find that attention-based architectures that jointly process a featurized representation of observations and actions have a better inductive bias for zero-shot coordination. Through fine-grained evaluation and scenario analysis, we show that the resulting policies are human-interpretable. Moreover, such agents coordinate with people without training on any human data.

In order for humans to confidently decide where to employ RL agents for real-world tasks, a human developer must validate that the agent will perform well at test-time. Some policy interpretability methods facilitate this by capturing the policy's decision making in a set of agent rollouts. However, even the most informative trajectories of training time behavior may give little insight into the agent's behavior out of distribution. In contrast, our method conveys how the agent performs under distribution shifts by showing the agent's behavior across a wider trajectory distribution. We generate these trajectories by guiding the agent to more diverse unseen states and showing the agent's behavior there. In a user study, we demonstrate that our method enables users to score better than baseline methods on one of two agent validation tasks.

Cooperative artificial intelligence with human or superhuman proficiency in collaborative tasks stands at the frontier of machine learning research. Prior work has tended to evaluate cooperative AI performance under the restrictive paradigms of self-play (teams composed of agents trained together) and cross-play (teams of agents trained independently but using the same algorithm). Recent work has indicated that AI optimized for these narrow settings may make for undesirable collaborators in the real-world. We formalize an alternative criteria for evaluating cooperative AI, referred to as inter-algorithm cross-play, where agents are evaluated on teaming performance with all other agents within an experiment pool with no assumption of algorithmic similarities between agents. We show that existing state-of-the-art cooperative AI algorithms, such as Other-Play and Off-Belief Learning, under-perform in this paradigm. We propose the Any-Play learning augmentation -- a multi-agent extension of diversity-based intrinsic rewards for zero-shot coordination (ZSC) -- for generalizing self-play-based algorithms to the inter-algorithm cross-play setting. We apply the Any-Play learning augmentation to the Simplified Action Decoder (SAD) and demonstrate state-of-the-art performance in the collaborative card game Hanabi.

Reasoning about uncertainty is vital in many real-life autonomous systems. However, current state-of-the-art planning algorithms cannot either reason about uncertainty explicitly, or do so with a high computational burden. Here, we focus on making informed decisions efficiently, using reward functions that explicitly deal with uncertainty. We formulate an approximation, namely an abstract observation model, that uses an aggregation scheme to alleviate computational costs. We derive bounds on the expected information-theoretic reward function and, as a consequence, on the value function. We then propose a method to refine aggregation to achieve identical action selection with a fraction of the computational time.

Atlassian today announced that it has acquired Percept.AI, an AI company from Y Combinator's summer 2017 batch, that offers an automated virtual agent support solution -- a chatbot, basically -- based on a proprietary AI engine for natural language understanding. Atlassian plans to integrate this virtual agent technology into Jira Service Management, its tool for helping IT teams provide better service to employees and customers. Ahead of today's acquisition, Percept had raised a seed round for an undisclosed amount from the likes of Hike Ventures, Builders VC, Cherubic Ventures, Amino Captial, Tribe Capital and Y Combinator, according to Crunchbase. The two companies did not disclose the financial details of today's acquisition. There can be little doubt that Atlassian is investing heavily in Jira Service Management.