In this paper, we introduce a generic and fresh model for distributed planning called "Distributed Planning Through Graph Merging" ({\sf DPGM}). This model unifies the different steps of the distributed planning process into a single step. Our approach is based on a planning graph structure for the agent reasoning and a CSP mechanism for the individual plan extraction and the coordination. We assume that no agent can reach the global goal alone. Therefore the agents must cooperate, {\it i.e.,} take in into account potential positive interactions between their activities to reach their common shared goal. The originality of our model consists in considering as soon as possible, {\it i.e.,} in the individual planning process, the positive and the negative interactions between agents activities in order to reduce the search cost of a global coordinated solution plan.

The purpose of the paper is to introduce a new approach of planning called Assumption-Based Planning. This approach is a very interesting way to devise a planner based on a multi-agent system in which the production of a global shared plan is obtained by conjecture/refutation cycles. Contrary to classical approaches, our contribution relies on the agents reasoning that leads to the production of a plan from planning domains. To take into account complex environments and the partial agents knowledge, we propose to consider the planning problem as a defeasible reasoning where the agents exchange proposals and counter-proposals and are able to reason about uncertainty. The argumentation dialogue between agents must not be viewed as a negotiation process but as an investigation process in order to build a plan. In this paper, we focus on the mechanisms that allow an agent to produce `reasonable' proposals according to its knowledge.

Most of the works on planning and learning, e.g., planning by (model based) reinforcement learning, are based on two main assumptions: (i) the set of states of the planning domain is fixed; (ii) the mapping between the observations from the real word and the states is implicitly assumed, and is not part of the planning domain. Consequently, the focus is on learning the transitions between states. Current approaches address neither the problem of learning new states of the planning domain, nor the problem of representing and updating the mapping between the real world perceptions and the states. In this paper, we drop such assumptions. We provide a formal framework in which (i) the agent can learn dynamically new states of the planning domain; (ii) the mapping between abstract states and the perception from the real world, represented by continuous variables, is part of the planning domain; (iii) such mapping is learned and updated along the "life" of the agent. We define and develop an algorithm that interleaves planning, acting, and learning. We provide a first experimental evaluation that shows how this novel framework can effectively learn coherent abstract planning models.

In order to engender trust in AI, humans must understand what an AI system is trying to achieve, and why. To overcome this problem, the underlying AI process must produce justifications and explanations that are both transparent and comprehensible to the user. AI Planning is well placed to be able to address this challenge. In this paper we present a methodology to provide initial explanations for the decisions made by the planner. Explanations are created by allowing the user to suggest alternative actions in plans and then compare the resulting plans with the one found by the planner. The methodology is implemented in the new XAI-Plan framework.

Efficiently scheduling data processing jobs on distributed compute clusters requires complex algorithms. Current systems, however, use simple generalized heuristics and ignore workload structure, since developing and tuning a bespoke heuristic for each workload is infeasible. In this paper, we show that modern machine learning techniques can generate highly-efficient policies automatically. Decima uses reinforcement learning (RL) and neural networks to learn workload-specific scheduling algorithms without any human instruction beyond specifying a high-level objective such as minimizing average job completion time. Off-the-shelf RL techniques, however, cannot handle the complexity and scale of the scheduling problem. To build Decima, we had to develop new representations for jobs' dependency graphs, design scalable RL models, and invent new RL training methods for continuous job arrivals. Our prototype integration with Spark on a 25-node cluster shows that Decima outperforms several heuristics, including hand-tuned ones, by at least 21%. Further experiments with an industrial production workload trace demonstrate that Decima delivers up to a 17% reduction in average job completion time and scales to large clusters.

AI (artificial intelligence) is perhaps one of the biggest trends to watch in the months to come, with many analysts predicting growth and technology providers making big moves in this area. PwC even suggests that global GDP will be 14% higher in 2030 as a result of AI, which is the equivalent of an additional $15.7 trillion. One big area in construction that is set to change is scheduling, with a new acquisition that happened this week. InEight announced it acquired BASIS, a company that purpose-built an AI planning software tool for the construction industry. The software captures insights and learnings from prior projects and uses the knowledge to make informed suggestions during the planning process.

AI (artificial intelligence) is perhaps one of the biggest trends to watch in the months to come, with many analysts predicting growth and technology providers making big moves in this area. PwC even suggests that global GDP will be 14% higher in 2030 as a result of AI, which is the equivalent of an additional $15.7 trillion. One big area in construction that is set to change is scheduling, with a new acquisition that happened this week. InEight announced it acquired BASIS, a company that purpose-built an AI planning software tool for the construction industry. The software captures insights and learnings from prior projects and uses the knowledge to make informed suggestions during the planning process.

Challenges for physical solitaire puzzle games are typically designed in advance by humans and limited in number. Alternately, some games incorporate stochastic setup rules, where the human solver randomly sets up the game board before solving the challenge, which can greatly increase the number of possible challenges. However, these setup rules can often generate unsolvable or uninteresting challenges. To better understand these setup processes, we apply a taxonomy for procedural content generation algorithms to solitaire puzzle games. In particular, for the game Fujisan, we examine how different stochastic challenge generation algorithms attempt to minimize undesirable challenges, and we report their affect on ease of physical setup, challenge solvability, and challenge difficulty. We find that algorithms can be simple for the solver yet generate solvable and difficult challenges, by constraining randomness through embedding sub-elements of the puzzle mechanics into the physical pieces of the game.

Real time strategy games are among the most challenging for artificial intelligence development and research. The need to manage resources and agent co-ordination in this genre still presents real challenges to even the most state of the art techniques in AI. My recent series on the AI of Total War highlights the continued efforts by series developers Creative Assembly to improve and expand the suite of AI systems required to craft the epic battles and nuanced diplomacy players comes to expect from that franchise. Today I want to look at this same issue from a research perspective, with a particular focus on the franchise that is arguably most synonymous with the genre: Blizzard's StarCraft. I want to take a look at the challenges this series presents to AI research and the significant efforts made in developing new AI techniques that adopts StarCraft as a test-bed. It's important that this be re-iterated at time when mass media rhetoric suggests the recent interest by the likes of Google DeepMind is the first real exploration of the problem.

Hierarchical planners that produce interpretable and appropriate plans are desired, especially in its application to supporting human decision making. In the typical development of the hierarchical planners, higher-level planners and symbol grounding functions are manually created, and this manual creation requires much human effort. In this paper, we propose a framework that can automatically refine symbol grounding functions and a high-level planner to reduce human effort for designing these modules. In our framework, symbol grounding and high-level planning, which are based on manually-designed knowledge bases, are modeled with semi-Markov decision processes. A policy gradient method is then applied to refine the modules, in which two terms for updating the modules are considered. The first term, called a reinforcement term, contributes to updating the modules to improve the overall performance of a hierarchical planner to produce appropriate plans. The second term, called a penalty term, contributes to keeping refined modules consistent with the manually-designed original modules. Namely, it keeps the planner, which uses the refined modules, producing interpretable plans. We perform preliminary experiments to solve the Mountain car problem, and its results show that a manually-designed high-level planner and symbol grounding function were successfully refined by our framework.