Services:- The service management capabilities help service departments provide support for service operations, contract management, service planning, tracking of customer interaction, activities, and customer support. Sales:- Provides all the tools to help efficiently manage your complete sales processing and customer lifecycle. From quotes to orders to deliveries to invoices, SAP Business One offers all the specified functions to simply manage the entire order-to-payment process. Manufacturing:- Offers an easy yet powerful planning system that helps production planners or buyers schedule and manage items for production or purchasing supported a spread of criteria. Purchasing:- The ERP software provides your small business with the tools that it must handle its entire procurement process, including orders, receipts, invoices, and payments.

Search is an important tool for computing effective policies in single- and multi-agent environments, and has been crucial for achieving superhuman performance in several benchmark fully and partially observable games. However, one major limitation of prior search approaches for partially observable environments is that the computational cost scales poorly with the amount of hidden information. In this paper we present \emph{Learned Belief Search} (LBS), a computationally efficient search procedure for partially observable environments. Rather than maintaining an exact belief distribution, LBS uses an approximate auto-regressive counterfactual belief that is learned as a supervised task. In multi-agent settings, LBS uses a novel public-private model architecture for underlying policies in order to efficiently evaluate these policies during rollouts. In the benchmark domain of Hanabi, LBS can obtain 55% ~ 91% of the benefit of exact search while reducing compute requirements by $35.8 \times$ ~ $4.6 \times$, allowing it to scale to larger settings that were inaccessible to previous search methods.

Automated planners are computer tools that allow autonomous agents to make strategies and decisions by determining a set of actions for the agent that to take, which will carry a system from a given initial state to the desired goal state. Many planners are domain-independent, allowing their deployment in a variety of domains. Such is the broad family of OPTIC planners. These planners perform Forward Search and call a Linear Programming (LP) solver multiple times at every state to check for consistency and to set bounds on the numeric variables. These checks can be computationally costly, especially in real-life applications. This paper suggests a method for identifying information about the specific state being evaluated, allowing the formulation of the equations to facilitate better solver selection and faster LP solving. The usefulness of the method is demonstrated in six domains and is shown to enhance performance significantly.

We tackle the problem of goal-directed graph construction: given a starting graph, a global objective function (e.g., communication efficiency), and a budget of modifications, the aim is to find a set of edges whose addition to the graph maximally improves the objective. This problem emerges in many networks of great importance for society such as transportation and critical infrastructure networks. We identify two significant shortcomings with present methods. Firstly, they focus exclusively on network topology while ignoring spatial information; however, in many real-world networks, nodes are embedded in space, which yields different global objectives and governs the range and density of realizable connections. Secondly, existing RL methods scale poorly to large networks due to the high cost of training a model and the scaling factors of the action space and global objectives. In this work, we formulate the problem of goal-directed construction of spatial networks as a deterministic MDP. We adopt the Monte Carlo Tree Search framework for planning in this domain, prioritizing the optimality of final solutions over the speed of policy evaluation. We propose several improvements over the standard UCT algorithm for this family of problems, addressing their single-agent nature, the trade-off between the costs of edges and their contribution to the objective, and an action space linear in the number of nodes. We demonstrate the suitability of this approach for improving the global efficiency and attack resilience of a variety of synthetic and real-world networks, including Internet backbone networks and metro systems. We obtain 24% better solutions on average compared to UCT on the largest networks tested, and scalability superior to previous methods.

Planning is hard. The use of subgoals can make planning more tractable, but selecting these subgoals is computationally costly. What algorithms might enable us to reap the benefits of planning using subgoals while minimizing the computational overhead of selecting them? We propose visual scoping, a strategy that interleaves planning and acting by alternately defining a spatial region as the next subgoal and selecting actions to achieve it. We evaluated our visual scoping algorithm on a variety of physical assembly problems against two baselines: planning all subgoals in advance and planning without subgoals. We found that visual scoping achieves comparable task performance to the subgoal planner while requiring only a fraction of the total computational cost. Together, these results contribute to our understanding of how humans might make efficient use of cognitive resources to solve complex planning problems.

Monte Carlo planners can often return sub-optimal actions, even if they are guaranteed to converge in the limit of infinite samples. Known asymptotic regret bounds do not provide any way to measure confidence of a recommended action at the conclusion of search. In this work, we prove bounds on the sub-optimality of Monte Carlo estimates for non-stationary bandits and Markov decision processes. These bounds can be directly computed at the conclusion of the search and do not require knowledge of the true action-value. The presented bound holds for general Monte Carlo solvers meeting mild convergence conditions. We empirically test the tightness of the bounds through experiments on a multi-armed bandit and a discrete Markov decision process for both a simple solver and Monte Carlo tree search.

We propose ScheduleNet, a RL-based real-time scheduler, that can solve various types of multi-agent scheduling problems. We formulate these problems as a semi-MDP with episodic reward (makespan) and learn ScheduleNet, a decentralized decision-making policy that can effectively coordinate multiple agents to complete tasks. The decision making procedure of ScheduleNet includes: (1) representing the state of a scheduling problem with the agent-task graph, (2) extracting node embeddings for agent and tasks nodes, the important relational information among agents and tasks, by employing the type-aware graph attention (TGA), and (3) computing the assignment probability with the computed node embeddings.

Prior to working in the automation space, I was a founder of two companies that developed data analytics, machine learning and AI technologies that focused on marketing, risk management and automated decision-making. I must admit, I didn't know much about RPA and automation tools back then, and neither did our developers. When I became a co-founder of Robocorp, I quickly learned that automation and AI are especially powerful together. I've also come to learn that there are many developers who don't know it yet. Each example listed above is a typical use of AI technology.

We investigate the use of multi-agent allocation techniques on problems related to Earth observation scenarios with multiple users and satellites. We focus on the problem of coordinating users having reserved exclusive orbit portions and one central planner having several requests that may use some intervals of these exclusives. We define this problem as Earth Observation Satellite Constellation Scheduling Problem (EOSCSP) and map it to a Mixed Integer Linear Program. As to solve EOSCSP, we propose market-based techniques and a distributed problem solving technique based on Distributed Constraint Optimization (DCOP), where agents cooperate to allocate requests without sharing their own schedules. These contributions are experimentally evaluated on randomly generated EOSCSP instances based on real large-scale or highly conflicting observation order books.

Robots will be expected to manipulate a wide variety of objects in complex and arbitrary ways as they become more widely used in human environments. As such, the rearrangement of objects has been noted to be an important benchmark for AI capabilities in recent years. We propose NeRP (Neural Rearrangement Planning), a deep learning based approach for multi-step neural object rearrangement planning which works with never-before-seen objects, that is trained on simulation data, and generalizes to the real world. We compare NeRP to several naive and model-based baselines, demonstrating that our approach is measurably better and can efficiently arrange unseen objects in fewer steps and with less planning time. Finally, we demonstrate it on several challenging rearrangement problems in the real world.