Because the groups are SMARTER when thinking TOGETHER than the individuals would be on their own.

Competitive sports are ultimately numbers games. Whether it's a gymnast racking up points on a balance beam, a tennis player acing her opponent, or a football team scoring on a last second Hail Mary, all matches are won and lost by numbers. There are upsets, comebacks, and situations when the losing team still seems to outperform the other -- but, even then, victory distills into digits. As such, it's obvious that many sports lend themselves nicely to the type of mathematical analyses that let keen-eyed statisticians predict outcomes -- maybe even exact scores -- just by crunching a bunch of numbers. After all, that's the basis of sports betting, and it's helped baseball managers craft winning teams on a tight budget just by considering little more than batting average, runs batted in, and stolen bases.

Deep reinforcement learning (RL) methods generally engage in exploratory behavior through noise injection in the action space. An alternative is to add noise directly to the agent's parameters, which can lead to more consistent exploration and a richer set of behaviors. Methods such as evolutionary strategies use parameter perturbations, but discard all temporal structure in the process and require significantly more samples. Combining parameter noise with traditional RL methods allows to combine the best of both worlds. We demonstrate that both off- and on-policy methods benefit from this approach through experimental comparison of DQN, DDPG, and TRPO on high-dimensional discrete action environments as well as continuous control tasks. Our results show that RL with parameter noise learns more efficiently than traditional RL with action space noise and evolutionary strategies individually.

This conclusion is based on a meta-analysis of the relationship between climate variables and natural selection measured in wild populations of invertebrates, plants, and vertebrates. Three aspects of this analysis cause concern: (i) lack of within-year climate variables, (ii) low and variable estimates of covariance relationships across taxa, and (iii) a lack of mechanistic explanations for the patterns observed; association is not causation.

The objective of this paper is to define an effective strategy for building an ensemble of Genetic Programming (GP) models. Ensemble methods are widely used in machine learning due to their features: they average out biases, they reduce the variance and they usually generalize better than single models. Despite these advantages, building ensemble of GP models is not a well-developed topic in the evolutionary computation community. To fill this gap, we propose a strategy that blends individuals produced by standard syntax-based GP and individuals produced by geometric semantic genetic programming, one of the newest semantics-based method developed in GP. In fact, recent literature showed that combining syntax and semantics could improve the generalization ability of a GP model. Additionally, to improve the diversity of the GP models used to build up the ensemble, we propose different pruning criteria that are based on correlation and entropy, a commonly used measure in information theory. Experimental results, obtained over different complex problems, suggest that the pruning criteria based on correlation and entropy could be effective in improving the generalization ability of the ensemble model and in reducing the computational burden required to build it.

AI has become "ALL IN" and pervading at a rapid speed. Technology moves at breakneck speed, and we now have more power in our pockets than we had in our homes in the 1990s. Artificial intelligence (AI) has been a fascinating concept of science fiction for decades, but many researchers think we're finally getting close to making AI a reality. NPR notes that in the last few years, scientists have made breakthroughs in "machine learning," using neural networks, which mimic the processes of real neurons. Artificial intelligence, defined as intelligence exhibited by machines, has many applications in today's society.

A Behavior Tree (BT) is a way to structure the switching between different tasks in an autonomous agent, such as a robot or a virtual entity in a computer game. BTs are a very efficient way of creating complex systems that are both modular and reactive. These properties are crucial in many applications, which has led to the spread of BT from computer game programming to many branches of AI and Robotics. In this book, we will first give an introduction to BTs, then we describe how BTs relate to, and in many cases generalize, earlier switching structures. These ideas are then used as a foundation for a set of efficient and easy to use design principles. Properties such as safety, robustness, and efficiency are important for an autonomous system, and we describe a set of tools for formally analyzing these using a state space description of BTs. With the new analysis tools, we can formalize the descriptions of how BTs generalize earlier approaches. We also show the use of BTs in automated planning and machine learning. Finally, we describe an extended set of tools to capture the behavior of Stochastic BTs, where the outcomes of actions are described by probabilities. These tools enable the computation of both success probabilities and time to completion.

Mutation is one of the most important stages of genetic algorithms because of its impact on the exploration of the search space, and in overcoming premature convergence. Since there are many types of mutations one common problem lies in selecting the appropriate type. The decision then becomes more difficult and needs more trial and error to find the best mutation to be used. This paper investigates the use of more than one mutation operator to enhance the performance of genetic algorithms. New mutation operators are proposed, in addition to two election strategies for the mutation operators. One is based on selecting the best mutation operator and the other randomly selects any operator. Several experiments were conducted on the Travelling Salesman Problem (TSP) to evaluate the proposed methods. These were compared to the well-known exchange mutation and rearrangement mutation. The results show the importance of some of the proposed methods, in addition to the significant enhancement of the genetic algorithms' performance, particularly when using more than one mutation operator.

Sand--bubblers are crabs of the genera Dotilla and Scopimera which are known to produce remarkable patterns and structures at tropical beaches. From these pattern-making abilities, we may draw inspiration for digital visual art. A simple mathematical model is proposed and an algorithm is designed that may create such sand-bubbler patterns artificially. In addition, design parameters to modify the patterns are identified and analyzed by computational aesthetic measures. Finally, an extension of the algorithm is discussed that may enable controlling and guiding generative evolution of the art-making process.

If you're placing any Golden Globes bets, then maybe you might want to consider what the latest A.I. predictions are saying. In both Golden Globes Best Picture categories -- comedy and drama -- Unanimous A.I. and applied their unique systems to forecast possible winners. And it looks like this year, you can place a lot of faith in a certain sea monster cleaning up. The Shape of Water is looking good in the categories of Best Actress, but also Best Picture, too. On Friday, in order to forecast possible outcomes in a variety of categories at the Golden Globes, Unanimous A.I. used what's known as "swarm intelligence."