Search is a core AI technique, especially in games [5, 27, 31] and domain-independent planning [3,12].

Physical spaces are increasingly dense with networked devices, promising seamless coordination and ambient intelligence. Yet today, cloud-first architectures force all communication through wide-area networks regardless of physical proximity. We lack an abstraction for spatial networking: using physical spaces to create boundaries for private, robust, and low-latency communication. We introduce $\textit{Bifröst}$, a programming model that realizes spatial networking using bigraphs to express both containment and connectivity, enabling policies to be scoped by physical boundaries, devices to be named by location, the instantiation of spatial services, and the composition of spaces while maintaining local autonomy. Bifröst enables a new class of spatially-aware applications, where co-located devices communicate directly, physical barriers require explicit gateways, and local control bridges to global coordination.

Search (PNS), are effective in playing and solving games. However, the understanding of their performance in industrial applications is still limited.

Bigraphical Reactive Systems (BRSs) are a graph-rewriting formalism describing systems evolving in two dimensions: spatially, e.g. a person in a room, and non-spatially, e.g. mobile phones communicating regardless of location. Despite use in domains including communication protocols, agent programming, biology, and security, there is no support for real-time systems. We extend BRSs to support real-time systems with a modelling approach that uses multiple perspectives to represent digital clocks. We use Action BRSs, a recent extension of BRSs, where the resulting transition system is a Markov Decision Process (MDP). This allows a natural representation of the choices in each system state: to either allow time to pass or perform a specific action. We implement our proposed approach using the BigraphER toolkit, and demonstrate the effectiveness through multiple examples including modelling cloud system requests.

Originality: PNS and related algorithms have not been evaluated for synthesis planning since work by Heifets and others several years ago. Revisiting this class of algorithms and proposing modifications to improve performance in multi-step synthesis planning is nice to see. Quality: The empirical evaluation is not as strong as it could be, but the conceptual contribution of this work is still important for the problem of synthesis planning. Clarity: The description of algorithms in 254-266 and elsewhere is not complete enough to reimplement the models and baselines. The dataset split, details of template extraction, network training, etc. is not provided either and the code is not available. Significance: The novelty of the modifications to the algorithm may be minor, but evaluating it in the context of this problem is important.

We present a novel form of Liquid Automata, using this to simulate autopoiesis, whereby living machines self-organise in the physical realm. This simulation is based on an earlier Cellular Automaton described by Francisco Varela. The basis of Liquid Automata is a particle simulation with additional rules about how particles are transformed on collision with other particles. Unlike cellular automata, there is no fixed grid or time-step, only particles moving about and colliding with each other in a continuous space/time.

We argue that chemistry should be the next grand challenge for Artificial Intelligence. The AI research community and humanity would benefit tremendously from focusing AI research on chemistry on a regular basis, as a benchmark as well as a real-world application domain. To support our position, we review the importance of chemical compound discovery and synthesis planning and discuss the properties of search spaces in a chemistry problem. Knowledge acquired in domains such as two-player board games or single-player puzzles places the AI community in a good position to solve critical problems in the chemistry domain. Yet, we show that searching in chemistry problems poses significant additional challenges that will have to be addressed. Finally, we envision how several AI areas like Natural Language Processing, Machine Learning, planning and search, are relevant for chemistry.

We describe a fully data driven model that learns to perform a retrosynthetic reaction prediction task, which is treated as a sequence-to-sequence mapping problem. The end-to-end trained model has an encoder-decoder architecture that consists of two recurrent neural networks, which has previously shown great success in solving other sequence-to-sequence prediction tasks such as machine translation. The model is trained on 50,000 experimental reaction examples from the United States patent literature, which span 10 broad reaction types that are commonly used by medicinal chemists. We find that our model performs comparably with a rule-based expert system baseline model, and also overcomes certain limitations associated with rule-based expert systems and with any machine learning approach that contains a rule-based expert system component. Our model provides an important first step towards solving the challenging problem of computational retrosynthetic analysis.

Akihiro Kishimoto is a research staff member at IBM Research – Ireland working on a range of projects in artificial intelligence, parallel and distributed computing and search. His interest in these technical fields grew from his passion for board games. And while a student at the University of Tokyo, he and three of his fellow classmates designed ISshogi, a program to play the incredibly complex (and ancient) Japanese board game, Shogi. ISshogi won the World Computer Shogi Championships four times from 1997-2005. While studying AI at the University of Alberta, Akihiro was a member of the GAMES group (Game-playing, Analytical methods, Minimax search and Empirical Studies) in the Department of Computing Science, and worked with Jonathan Schaeffer and others to solve Checkers.

Event-driven automation of reactive functionalities for complex event processing is an urgent need in today's distributed service-oriented architectures and Web-based event-driven environments. An important problem to be addressed is how to correctly and efficiently capture and process the event-based behavioral, reactive logic embodied in reaction rules, and combining this with other conditional decision logic embodied, e.g., in derivation rules. This paper elaborates a homogeneous integration approach that combines derivation rules, reaction rules and other rule types such as integrity constraints into the general framework of logic programming, the industrial-strength version of declarative programming. We describe syntax and semantics of the language, implement a distributed web-based middleware using enterprise service technologies and illustrate its adequacy in terms of expressiveness, efficiency and scalability through examples extracted from industrial use cases. The developed reaction rule language provides expressive features such as modular ID-based updates with support for external imports and self-updates of the intensional and extensional knowledge bases, transactions including integrity testing and roll-backs of update transition paths. It also supports distributed complex event processing, event messaging and event querying via efficient and scalable enterprise middleware technologies and event/action reasoning based on an event/action algebra implemented by an interval-based event calculus variant as a logic inference formalism.