The model selection procedure is usually a single-criterion decision making in which we select the model that maximizes a specific metric in a specific set, such as the Validation set performance. We claim this is very naive and can perform poor selections of over-fitted models due to the over-searching phenomenon, which over-estimates the performance on that specific set. Futhermore, real world data contains noise that should not be ignored by the model selection procedure and must be taken into account when performing model selection. Also, we have defined four theoretical optimality conditions that we can pursue to better select the models and analyze them by using a multi-criteria decision-making algorithm (TOPSIS) that considers proxies to the optimality conditions to select reasonable models.

Video games have proved to be a very defying laboratory to study machine-learning techniques, such as Deep Reinforcement Learning (DRL) algorithms. This paper presents a new approach for a DRL-based agent trained through Deep Q-Network (DQN) technique to perform free kicks in FIFA 18 game. The main motivation for choosing this case study is the fact that, like in many situations of the real life, FIFA represents a stochastic environment. Coping with this task, the main contributions of the present paper consist on: inspired on the OpenAI Gym and on the OpenAI Universe platforms, implementing a new user-friendly interface (in terms of portability and use simplicity) to connect the learning module with the 3D FIFA's game environment; implementing a DRL-based agent for free kicks in FIFA that uses two distinct data representations retrieved from lower cost computational procedures. The results were validated through two evaluative parameters: score of well succeed kicks and training time.

This paper presents an ongoing study in the area of Human-Robot Collaboration, more precisely collaborative manipulation tasks between one robot and multiple people. We study how different trajectories influence people's perception of the robot's goal. To achieve this, we propose an approach based on Probabilistic Motor Primitives and the notion of legibility and predictability of trajectories to create the movements the robot performs during task execution. In this approach we also propose combining of legible and predictable trajectories depending on the state of the task in order to diminish the drawbacks associated with each type of trajectory.

The fact that machine learning development focuses on hyperparameter tuning and data pipelines does not mean that we need to reinvent the wheel or look for a completely new way. According to Thiago de Faria, DevOps lays a strong foundation: culture change to support experimentation, continuous evaluation, sharing, abstraction layers, observability, and working in products and services. Thiago de Faria, DataOps and AI lead at LINKIT, spoke about AI with a DevOps mindset at Codemotion Berlin 2018. InfoQ is covering this conference with Q&A, summaries, and articles. Developing apps with if/elses, loops and deterministic functions encapsulate the vast majority of cases in the industry.