Expert imitation, behavioral diversity, and fairness preferences give rise to preferences in sequential decision making domains that do not decompose additively across time. We introduce the class of convex Markov games that allow general convex preferences over occupancy measures. Despite infinite time horizon and strictly higher generality than Markov games, pure strategy Nash equilibria exist under strict convexity. Furthermore, equilibria can be approximated efficiently by performing gradient descent on an upper bound of exploitability. Our experiments imitate human choices in ultimatum games, reveal novel solutions to the repeated prisoner's dilemma, and find fair solutions in a repeated asymmetric coordination game. In the prisoner's dilemma, our algorithm finds a policy profile that deviates from observed human play only slightly, yet achieves higher per-player utility while also being three orders of magnitude less exploitable.

Abstract-- This paper investigates the use of a samplingbased approach, the RRT*, to reconfigure a 2D set of connected tiles in complex environments, where multiple obstacles might be present. Since the target application is automated building of discrete, cellular structures using mobile robots, there are constraints that determine what tiles can be picked up and where they can be dropped off during reconfiguration. We compare our approach to two algorithms as global and local planners, and show that we are able to find more efficient build sequences using a reasonable number of samples, in environments with varying densities of obstacles. Cellular structures are related to reconfigurable robotics work, but rather than using intelligent, powered and actuated reconfigurable modules, small robots that walk along the modules are used to move them. This allows the modules to be passive, which reduces their complexity, weight, and cost.

Robot failures in human-centered environments are inevitable. Therefore, the ability of robots to explain such failures is paramount for interacting with humans to increase trust and transparency. To achieve this skill, the main challenges addressed in this paper are I) acquiring enough data to learn a cause-effect model of the environment and II) generating causal explanations based on that model. We address I) by learning a causal Bayesian network from simulation data. Concerning II), we propose a novel method that enables robots to generate contrastive explanations upon task failures. The explanation is based on setting the failure state in contrast with the closest state that would have allowed for a successful execution. This state is found through breadth-first search and is based on success predictions from the learned causal model. We assessed our method in two different scenarios I) stacking cubes and II) dropping spheres into a container. The obtained causal models reach a sim2real accuracy of 70% and 72%, respectively. We finally show that our novel method scales over multiple tasks and allows real robots to give failure explanations like 'the upper cube was stacked too high and too far to the right of the lower cube.'

In this special guest feature, Anar Mammadov, Founder of Senpex, highlights how delivery logistics companies have powerful artificial intelligence, data analysis tools at their disposal, and part of the innovation in this field has been ensuring that clients can access this data. Anar is a Software development professional with more than 15 years of extensive experience in enterprise solutions & mobile app development. In addition to his extensive software experience, he is a practical and result-oriented business owner. Senpex Technology is a new web-based and mobile app, to provide personalized courier delivery and logistics services to our customers with ease and cost-effectiveness. Senpex can be utilized 24/7, no interruptions in your delivery needs.

In integrative analyses of omics data, it is often of interest to extract data embedding from one data type that best reflect relations with another data type. This task is traditionally fulfilled by linear methods such as canonical correlation and partial least squares. However, information contained in one data type pertaining to the other data type may not be in the linear form. Deep learning provides a convenient alternative to extract nonlinear information. Here we develop a method Autoencoder-based Integrative Multi-omics data Embedding (AIME) to extract such information. Using a real gene expression - methylation dataset, we show that AIME extracted meaningful information that the linear approach could not find. The R implementation is available at http://web1.sph.emory.edu/users/tyu8/AIME/.