The interview is one of the most fundamental aspects of an organization's hiring process, but getting those appointments on everyone's calendars can be a logistical nightmare. And relying on a tedious manual system may leave candidates with a bad first impression. "People don't have their calendars up-to-date, or they cancel and reschedule constantly," says Lin Lin Phan, talent operations manager at MuleSoft, a San Francisco-based technology firm. "Things happen, and we're the ones who have to step in and find a replacement interviewer before it has a negative effect on the candidate's experience." Fortunately, technology can help with automation tools that streamline the scheduling process.

Linear Squared, a Sri Lankan company offering Machine Learning and Advanced Data Analytics solutions, has launched a fully automated planning platform for apparel industry. The company claims the solution, Capacity Squared, to be the world's first AI driven production planning software. The process of capacity planning on a shopfloor has always been manual, which consumes more time and is prone to human errors and biases. In unforeseeable situations like delay of raw materials, missed targets etc., sometimes even the well-planned schedule runs on low efficiency. Thus, the solution lies in the optimisation of the planning schedule without expanding the factory by adding new machinery or hiring labour.

In Reinforcement Learning, the agents take random decisions in their environment and learns on selecting the right one out of many to achieve their goal and play at a super-human level. Policy and Value Networks are used together in algorithms like Monte Carlo Tree Search to perform Reinforcement Learning. Both the networks are an integral part of a method called Exploration in MCTS algorithm. They are also known as policy iteration & value iteration since they are calculated many times making it an iterative process. Let's understand why are they so important in Machine Learning and what's the difference between them?

Artificial Intelligence (AI) has already started to influence processes and automate decision making in manufacturing, health care, finance and customer service industries. By many measures, HR appears to be next on that list. While the technology is still nascent, the building blocks exist to suggest that machine learning could ease the burden of complex analysis, surface insights, and trigger actions on behalf of managers in the workplace. One way is by comparing real-time data to historical data or benchmarks to identify statistically significant deviations from the norm. For example, if scheduled labor hours as a percent of sales is significantly higher than the norm in a group of stores, the system can detect this and send that information proactively to management. Another way is to take a series of interrelated decisions and use algorithms to model scenarios.

Welcome to part 4 of my series on the AI of Total War. A game that completely re-built the campaign AI systems to accommodate for an increasingly more complex series of mechanics, resources and consequences. Rome II's adoption of the Monte Carlo Tree Search (MCTS) algorithm is a critical step in bring the campaign AI up to spec for more contemporary entries in the series. In this entry I'm going to look at how the MCTS systems were improved upon, as well as how the diplomacy systems have been scaled up for the modern era as Rome gave way to 2015's Total War: Attila. Attila is the ninth entry in the Total War franchise and transposes the conflict to the late 4th and early 5th century: an phase of history known as the Migration Period.

The state of the art practice in robotics planning is to script behaviors manually, where each behavior is typically generated using trajectory optimization. However, in order for robots to be able to act robustly and adapt to novel situations, they need to plan these activity sequences autonomously. Since the conditions and effects of these behaviors are tightly coupled through time, state and control variables, many problems require that the tasks of activity planning and trajectory optimization are considered together. There are two key issues underlying effective hybrid activity and trajectory planning: the sufficiently accurate modeling of robot dynamics and the capability of planning over long horizons. Hybrid activity and trajectory planners that employ mixed integer programming within a discrete time formulation are able to accurately model complex dynamics for robot vehicles, but are often restricted to relatively short horizons. On the other hand, current hybrid activity planners that employ continuous time formulations can handle longer horizons but they only allow actions to have continuous effects with constant rate of change, and restrict the allowed state constraints to linear inequalities. This is insufficient for many robotic applications and it greatly limits the expressivity of the problems that these approaches can solve. In this work we present the ScottyActivity planner, that is able to generate practical hybrid activity and motion plans over long horizons by employing recent methods in convex optimization combined with methods for planning with relaxed plan graphs and heuristic forward search. Unlike other continuous time planners, ScottyActivity can solve a broad class of robotic planning problems by supporting convex quadratic constraints on state variables and control variables that are jointly constrained and that affect multiple state variables simultaneously. In order to support planning over long horizons, ScottyActivity does not resort to time, state or control variable discretization. While straightforward formulations of consistency checks are not convex and do not scale, we present an efficient convex formulation, in the form of a Second Order Cone Program (SOCP), that is very fast to solve. We also introduce several new realistic domains that demonstrate the capabilities and scalability of our approach, and their simplified linear versions, that we use to compare with other state of the art planners. This work demonstrates the power of integrating advanced convex optimization techniques with discrete search methods and paves the way for extensions dealing with non-convex disjoint constraints, such as obstacle avoidance.

In this paper, we propose a learning algorithm that speeds up the search in task and motion planning problems. Our algorithm proposes solutions to three different challenges that arise in learning to improve planning efficiency: what to predict, how to represent a planning problem instance, and how to transfer knowledge from one problem instance to another. We propose a method that predicts constraints on the search space based on a generic representation of a planning problem instance, called score-space, where we represent a problem instance in terms of the performance of a set of solutions attempted so far. Using this representation, we transfer knowledge, in the form of constraints, from previous problems based on the similarity in score space. We design a sequential algorithm that efficiently predicts these constraints, and evaluate it in three different challenging task and motion planning problems. Results indicate that our approach performs orders of magnitudes faster than an unguided planner

Today's automated vehicles lack the ability to cooperate implicitly with others. This work presents a Monte Carlo Tree Search (MCTS) based approach for decentralized cooperative planning using macro-actions for automated vehicles in heterogeneous environments. Based on cooperative modeling of other agents and Decoupled-UCT (a variant of MCTS), the algorithm evaluates the state-action-values of each agent in a cooperative and decentralized manner, explicitly modeling the interdependence of actions between traffic participants. Macro-actions allow for temporal extension over multiple time steps and increase the effective search depth requiring fewer iterations to plan over longer horizons. Without predefined policies for macro-actions, the algorithm simultaneously learns policies over and within macro-actions. The proposed method is evaluated under several conflict scenarios, showing that the algorithm can achieve effective cooperative planning with learned macro-actions in heterogeneous environments.

Counterexample-guided abstraction refinement (CEGAR) is a method for incrementally computing abstractions of transition systems. We propose a CEGAR algorithm for computing abstraction heuristics for optimal classical planning. Starting from a coarse abstraction of the planning task, we iteratively compute an optimal abstract solution, check if and why it fails for the concrete planning task and refine the abstraction so that the same failure cannot occur in future iterations. A key ingredient of our approach is a novel class of abstractions for classical planning tasks that admits efficient and very fine-grained refinement. Since a single abstraction usually cannot capture enough details of the planning task, we also introduce two methods for producing diverse sets of heuristics within this framework, one based on goal atoms, the other based on landmarks. In order to sum their heuristic estimates admissibly we introduce a new cost partitioning algorithm called saturated cost partitioning. We show that the resulting heuristics outperform other state-of-the-art abstraction heuristics in many benchmark domains.

Pieter Abbeel UC Berkeley In recent years, deep generative models have been shown to'imagine' convincing high-dimensional observations such as images, audio, and even video, learning directly from raw data. In this work, we ask how to imagine goal-directed visual plans - a plausible sequence of observations that transition a dynamical system from its current configuration to a desired goal state, which can later be used as a reference trajectory for control. We focus on systems with high-dimensional observations, such as images, and propose an approach that naturally combines representation learning and planning. Our framework learns a generative model of sequential observations, where the generative process is induced by a transition in a low-dimensional planning model, and an additional noise. By maximizing the mutual information between the generated observations and the transition in the planning model, we obtain a low-dimensional representation that best explains the causal nature of the data. We structure the planning model to be compatible with efficient planning algorithms, and we propose several such models based on either discrete or continuous states. Finally, to generate a visual plan, we project the current and goal observations onto their respective states in the planning model, plan a trajectory, and then use the generative model to transform the trajectory to a sequence of observations. We demonstrate our method on imagining plausible visual plans of rope manipulation.