The ability to infer the intentions of others, predict their goals, and deduce their plans are critical features for intelligent agents. For a long time, several approaches investigated the use of symbolic representations and inferences with limited success, principally because it is difficult to capture the cognitive knowledge behind human decisions explicitly. The trend, nowadays, is increasingly focusing on learning to infer intentions directly from data, using deep learning in particular. We are now observing interesting applications of intent classification in natural language processing, visual activity recognition, and emerging approaches in other domains. This paper discusses a novel approach combining few-shot and transfer learning with cross-domain features, to learn to infer the intent of an agent navigating in physical environments, executing arbitrary long sequences of actions to achieve their goals. Experiments in synthetic environments demonstrate improved performance in terms of learning from few samples and generalizing to unseen configurations, compared to a deep-learning baseline approach.

Generalized planning aims at computing an algorithm-like structure (generalized plan) that solves a set of multiple planning instances. In this paper we define negative examples for generalized planning as planning instances that must not be solved by a generalized plan. With this regard the paper extends the notion of validation of a generalized plan as the problem of verifying that a given generalized plan solves the set of input positives instances while it fails to solve a given input set of negative examples. This notion of plan validation allows us to define quantitative metrics to asses the generalization capacity of generalized plans. The paper also shows how to incorporate this new notion of plan validation into a compilation for plan synthesis that takes both positive and negative instances as input. Experiments show that incorporating negative examples can accelerate plan synthesis in several domains and leverage quantitative metrics to evaluate the generalization capacity of the synthesized plans.

MELVILLE, N.Y., November 18, 2019 – Effectively managing today's workforce is crucial for improving customer experience, operational efficiency, and compliance. Yet currently, rising expectations of both customers and employees have made forecasting and scheduling contact center agents and customer engagement resources exponentially more challenging. To give companies a simpler way to manage work across the enterprise, Verint Systems Inc. (Nasdaq: VRNT), The Customer Engagement Company, today announced the newest release of its market-leading Workforce Management (WFM) solution, which leverages artificial intelligence-infused automation and new mobile tools to streamline forecasting and scheduling and improve employee engagement, all easily accessible via the Verint Cloud. "The workforce represents up to 80 percent of overall contact center budgets so accurate and cost-effective scheduling is vital," says Verint's John Goodson, SVP and general manager, Products. "At the same time, today's employees demand easier flex scheduling options, so organizations must balance flexibility and cost to provide superior service. As a pioneer in WFM, we view this new release as one that can invigorate the market to meet the ever-changing demands of today's contact centers and throughout the enterprise."

CPG executives are painfully aware that they're investing billions of dollars in trade promotions each year, but as many as 72% fail to break even¹. It's clear that promotions have become more complex and harder to manage as CPGs must respond to changing consumer behavior, increasing demands from retailers and blurring of physical and online channels. Traditional forecasting and promotion-planning systems are unable to provide real-time, accurate insights to help managers understand the big picture. Below, we'll explore seven ways in which AI can help CPG companies more effectively plan promotional events, measure outcomes and make adjustments. You can read more in the companion paper on how AI transforms promotional trade funds management.

Planning algorithms based on lookahead search have achieved remarkable successes in artificial intelligence. Human world champions have been defeated in classic games such as checkers [34], chess [5], Go [38] and poker [3, 26], and planning algorithms have had real-world impact in applications from logistics [47] to chemical synthesis [37]. However, these planning algorithms all rely on knowledge of the environment's dynamics, such as the rules of the game or an accurate simulator, preventing their direct application to real-world domains like robotics, industrial control, or intelligent assistants. Model-based reinforcement learning (RL) [42] aims to address this issue by first learning a model of the environment's dynamics, and then planning with respect to the learned model. Typically, these models have either focused on reconstructing the true environmental state [8, 16, 24], or the sequence of full observations [14, 20]. However, prior work [4, 14, 20] remains far from the state of the art in visually rich domains, such as Atari 2600 games [2]. Instead, the most successful methods are based on model-free RL [9, 21, 18] - i.e. they estimate the optimal policy and/or value function directly from interactions with the environment. However, model-free algorithms are in turn far from the state of the art in domains that require precise and sophisticated lookahead, such as chess and Go. In this paper, we introduce MuZero, a new approach to model-based RL that achieves state-of-the-art performance in Atari 2600, a visually complex set of domains, while maintaining superhuman performance in precision planning tasks such as chess, shogi and Go.

Robustness Envelopes characterize the set of possible contingencies that a plan is able to address without re-planning, but their exact computation is extremely expensive; furthermore, general robustness envelopes are not amenable for efficient execution. In this paper, we present a novel, anytime algorithm to approximate Robustness Envelopes, making them scalable and executable. This is proven by an experimental analysis showing the efficiency of the algorithm, and by a concrete case study where the execution of robustness envelopes significantly reduces the number of re-plannings. 1 Introduction When planning and scheduling techniques are employed in practical applications, one of the major problems is the need for online re-planning when the observed contingencies are not aligned with the ones that were considered at planning time. These situations are common, because it is arguably impossible to predict the entire range of situations an autonomous system can encounter, especially when the planning domain encompasses time and temporal constraints. Unfortunately, re-planning can be costly in terms of time, and computational resources can be scarce on-board, so limiting the use of re-planning is very important for practical purposes. In principle, it is also possible to continue with the execution of a plan even when the observed contingencies are unexpected, optimistically hoping for a successful completion. However, this approach offers no formal guarantee, and is prone to the risk of continuing execution of a plan that is bound to fail. Several approaches have been proposed in the literature to address this problem (see (In-grand and Ghallab 2017) for a survey focused on robotics).

This work aims to make plan recognition as planning more ready for real-world scenarios by adapting previous compilations to work with partial-order, half-seen observations of both fluents and actions. We first redefine what observations can be and what it means to satisfy each kind. We then provide a compilation from plan recognition problem to classical planning problem, similar to original work by Ramirez and Geffner, but accommodating these more complex observation types. This compilation can be adapted towards other planning-based plan recognition techniques. Lastly we evaluate this method against an "ignore complexity" strategy that uses the original method by Ramirez and Geffner. Our experimental results suggest that, while slower, our method is equally or more accurate than baseline methods; our technique sometimes significantly reduces the size of the solution to the plan recognition problem, i.e, the size of the optimal goal set. We discuss these findings in the context of plan recognition problem difficulty and present an avenue for future work.

The research in hierarchical planning has made considerable progress in the last few years. Many recent systems do not rely on hand-tailored advice anymore to find solutions, but are supposed to be domain-independent systems that come with sophisticated solving techniques. In principle, this development would make the comparison between systems easier (because the domains are not tailored to a single system anymore) and -- much more important -- also the integration into other systems, because the modeling process is less tedious (due to the lack of advice) and there is no (or less) commitment to a certain planning system the model is created for. However, these advantages are destroyed by the lack of a common input language and feature set supported by the different systems. In this paper, we propose an extension to PDDL, the description language used in non-hierarchical planning, to the needs of hierarchical planning systems. We restrict our language to a basic feature set shared by many recent systems, give an extension of PDDL's EBNF syntax definition, and discuss our extensions with respect to several planner-specific input languages from related work.

About 87% of marketing organizations have already started using some level of personalization. By 2024, AI identification of emotions is expected to influence more than 50% of online advertisements globally. Gartner has confirmed that AEI is among the key technology trends that are expected to witness tremendous growth in the next five years. Computer vision allows AI to interpret and manipulate physical environments, which is one of the key technologies used for emotion recognition. Artificial Emotional Intelligence (AEI) will sense customer emotions, based on which companies can influence buying decisions.

-- T o solve multi-step manipulation tasks in the real world, an autonomous robot must take actions to observe its environment and react to unexpected observations. This may require opening a drawer to observe its contents or moving an object out of the way to examine the space behind it. If the robot fails to detect an important object, it must update its belief about the world and compute a new plan of action. Additionally, a robot that acts noisily will never exactly arrive at a desired state. Still, it is important that the robot adjusts accordingly in order to keep making progress towards achieving the goal. In this work, we present an online planning and execution system for robots faced with these kinds of challenges. Our approach is able to efficiently solve partially observable problems both in simulation and in a real-world kitchen. Robots acting autonomously in human environments are faced with a variety of challenges. First, they must make both discrete decisions about what object to manipulate as well as continuous decisions about which motions to execute to achieve a desired interaction. Planning in these large hybrid spaces is the subject of integrated T ask and Motion Planning (T AMP) [1], [2], [3], [4], [5], [6].