Search

Automated decision-making is a fundamental topic that spans multiple sub-disciplines in AI: reinforcement learning (RL), AI planning (AP), foundation models, and operations research, among others. Despite recent efforts to ``bridge the gaps'' between these communities, there remain many insights that have not yet transcended the boundaries. Our goal in this paper is to provide a brief and non-exhaustive primer on ideas well-known in AP, but less so in other sub-disciplines. We do so by introducing the classical AP problem and representation, and extensions that handle uncertainty and time through the Markov Decision Process formalism. Next, we survey state-of-the-art techniques and ideas for solving AP problems, focusing on their ability to exploit problem structure. Lastly, we cover subfields within AP for learning structure from unstructured inputs and learning to generalise to unseen scenarios and situations.

Graph learning is naturally well suited for use in planning due to its ability to exploit relational structures exhibited in planning domains and to take as input planning instances with arbitrary number of objects. In this paper, we study the usage of graph learning for planning thus far by studying the theoretical and empirical effects on learning and planning performance of (1) graph representations of planning tasks, (2) graph learning architectures, and (3) optimisation formulations for learning. Our studies accumulate in the GOOSE framework which learns domain knowledge from small planning tasks in order to scale up to much larger planning tasks. In this paper, we also highlight and propose the 5 open challenges in the general Learning for Planning field that we believe need to be addressed for advancing the state-of-the-art.

Graph learning is naturally well suited for use in symbolic, object-centric planning due to its ability to exploit relational structures exhibited in planning domains and to take as input planning instances with arbitrary numbers of objects. Numeric planning is an extension of symbolic planning in which states may now also exhibit numeric variables. In this work, we propose data-efficient and interpretable machine learning models for learning to solve numeric planning tasks. This involves constructing a new graph kernel for graphs with both continuous and categorical attributes, as well as new optimisation methods for learning heuristic functions for numeric planning. Experiments show that our graph kernels are vastly more efficient and generalise better than graph neural networks for numeric planning, and also yield competitive coverage performance compared to domain-independent numeric planners. Code is available at https://github.com/DillonZChen/goose, Comment: Extended version of NeurIPS 2024 paper

In many automated planning applications, action costs can be hard to specify. An example is the time needed to travel through a certain road segment, which depends on many factors, such as the current weather conditions. A natural way to address this issue is to learn to predict these parameters based on input features (e.g., weather forecasts) and use the predicted action costs in automated planning afterward. Decision-Focused Learning (DFL) has been successful in learning to predict the parameters of combinatorial optimization problems in a way that optimizes solution quality rather than prediction quality. This approach yields better results than treating prediction and optimization as separate tasks. In this paper, we investigate for the first time the challenges of implementing DFL for automated planning in order to learn to predict the action costs. There are two main challenges to overcome: (1) planning systems are called during gradient descent learning, to solve planning problems with negative action costs, which are not supported in planning. We propose novel methods for gradient computation to avoid this issue. (2) DFL requires repeated planner calls during training, which can limit the scalability of the method. We experiment with different methods approximating the optimal plan as well as an easy-to-implement caching mechanism to speed up the learning process. As the first work that addresses DFL for automated planning, we demonstrate that the proposed gradient computation consistently yields significantly better plans than predictions aimed at minimizing prediction error; and that caching can temper the computation requirements.

Heuristic search is a powerful approach for solving planning problems and numeric planning is no exception. In this paper, we boost the performance of heuristic search for numeric planning with various powerful techniques orthogonal to improving heuristic informedness: numeric novelty heuristics, the Manhattan distance heuristic, and exploring the use of multi-queue search and portfolios for combining heuristics., Comment: Extended version of SoCS 2024 paper

Current approaches for learning for planning have yet to achieve competitive performance against classical planners in several domains, and have poor overall performance. In this work, we construct novel graph representations of lifted planning tasks and use the WL algorithm to generate features from them. These features are used with classical machine learning methods which have up to 2 orders of magnitude fewer parameters and train up to 3 orders of magnitude faster than the state-of-the-art deep learning for planning models. Our novel approach, WL-GOOSE, reliably learns heuristics from scratch and outperforms the $h^{\text{FF}}$ heuristic in a fair competition setting. It also outperforms or ties with LAMA on 4 out of 10 domains on coverage and 7 out of 10 domains on plan quality. WL-GOOSE is the first learning for planning model which achieves these feats. Furthermore, we study the connections between our novel WL feature generation method, previous theoretically flavoured learning architectures, and Description Logic Features for planning., Comment: Extended version of ICAPS 2024 paper

We present three novel graph representations of planning tasks suitable for learning domain-independent heuristics using Graph Neural Networks (GNNs) to guide search. In particular, to mitigate the issues caused by large grounded GNNs we present the first method for learning domain-independent heuristics with only the lifted representation of a planning task. We also provide a theoretical analysis of the expressiveness of our models, showing that some are more powerful than STRIPS-HGN, the only other existing model for learning domain-independent heuristics. Our experiments show that our heuristics generalise to much larger problems than those in the training set, vastly surpassing STRIPS-HGN heuristics., Comment: Extended version of AAAI 2024 paper

Model-based diagnosis has been an active research topic in different communities including artificial intelligence, formal methods, and control. This has led to a set of disparate approaches addressing different classes of systems and seeking different forms of diagnoses. In this paper, we resolve such disparities by generalising Reiter's theory to be agnostic to the types of systems and diagnoses considered. This more general theory of diagnosis from first principles defines the minimal diagnosis as the set of preferred diagnosis candidates in a search space of hypotheses. Computing the minimal diagnosis is achieved by exploring the space of diagnosis hypotheses, testing sets of hypotheses for consistency with the system's model and the observation, and generating conflicts that rule out successors and other portions of the search space. Under relatively mild assumptions, our algorithms correctly compute the set of preferred diagnosis candidates. The main difficulty here is that the search space is no longer a powerset as in Reiter's theory, and that, as consequence, many of the implicit properties (such as finiteness of the search space) no longer hold. The notion of conflict also needs to be generalised and we present such a more general notion. We present two implementations of these algorithms, using test solvers based on satisfiability and heuristic search, respectively, which we evaluate on instances from two real world discrete event problems. Despite the greater generality of our theory, these implementations surpass the special purpose algorithms designed for discrete event systems, and enable solving instances that were out of reach of existing diagnosis approaches.

Heuristic search is a powerful approach that has successfully been applied to a broad class of planning problems, including classical planning, multi-objective planning, and probabilistic planning modelled as a stochastic shortest path (SSP) problem. Here, we extend the reach of heuristic search to a more expressive class of problems, namely multi-objective stochastic shortest paths (MOSSPs), which require computing a coverage set of non-dominated policies. We design new heuristic search algorithms MOLAO* and MOLRTDP, which extend well-known SSP algorithms to the multi-objective case. We further construct a spectrum of domain-independent heuristic functions differing in their ability to take into account the stochastic and multi-objective features of the problem to guide the search. Our experiments demonstrate the benefits of these algorithms and the relative merits of the heuristics., Comment: 11 pages, 4 figures, 3 tables, accepted to AAAI23

We present SmartGridToolbox: a C++ library for simulating modern and future electricity networks. SmartGridToolbox is distinguished by the fact that it is a general purpose library (rather than an application), that emphasizes flexibility, extensibility, and ability to interface with a wide range of other tools, such as optimization technologies. It incorporates fully unbalanced network modelling, fast power flow and OPF solvers, a discrete-event simulation engine, and a component library that includes network components like lines, cables, transformers, ZIP loads and generators, renewable and storage components like PV generation and batteries, inverters, tap changers, PV, generic time dependent loads and more. We anticipate that SmartGridToolbox will be useful to researchers who require accurate simulations of electricity networks that go beyond simple applications of load flow - for example, by incorporating custom optimisation algorithms, controllers, devices, or network management strategies. Being a library, it is also perfect for developing a wide range of end use applications. We start with a comparison to existing open source software, and move on to present its main features and benchmark results. We conclude by discussing four applications, most notably, the use of SmartGridToolbox in the CONSORT Bruny Island Battery Trial, conducted between 2016 and 2019., Comment: 20 pages, 9 figures

We present the first approach capable of learning domain-independent planning heuristics entirely from scratch. The heuristics we learn map the hypergraph representation of the delete-relaxation of the planning problem at hand, to a cost estimate that approximates that of the least-cost path from the current state to the goal through the hypergraph. We generalise Graph Networks to obtain a new framework for learning over hypergraphs, which we specialise to learn planning heuristics by training over state/value pairs obtained from optimal cost plans. Our experiments show that the resulting architecture, STRIPS-HGNs, is capable of learning heuristics that are competitive with existing delete-relaxation heuristics including LM-cut. We show that the heuristics we learn are able to generalise across different problems and domains, including to domains that were not seen during training.

In this paper, we discuss the learning of generalised policies for probabilistic and classical planning problems using Action Schema Networks (ASNets). The ASNet is a neural network architecture that exploits the relational structure of (P)PDDL planning problems to learn a common set of weights that can be applied to any problem in a domain. By mimicking the actions chosen by a traditional, non-learning planner on a handful of small problems in a domain, ASNets are able to learn a generalised reactive policy that can quickly solve much larger instances from the domain. This work extends the ASNet architecture to make it more expressive, while still remaining invariant to a range of symmetries that exist in PPDDL problems. We also present a thorough experimental evaluation of ASNets, including a comparison with heuristic search planners on seven probabilistic and deterministic domains, an extended evaluation on over 18,000 Blocksworld instances, and an ablation study. Finally, we show that sparsity-inducing regularisation can produce ASNets that are compact enough for humans to understand, yielding insights into how the structure of ASNets allows them to generalise across a domain., Comment: Journal extension of AAAI'18 paper (arXiv:1709.04271)

Optimal planning with respect to learned neural network (NN) models in continuous action and state spaces using mixed-integer linear programming (MILP) is a challenging task for branch-and-bound solvers due to the poor linear relaxation of the underlying MILP model. For a given set of features, potential heuristics provide an efficient framework for computing bounds on cost (reward) functions. In this paper, we model the problem of finding optimal potential bounds for learned NN models as a bilevel program, and solve it using a novel finite-time constraint generation algorithm. We then strengthen the linear relaxation of the underlying MILP model by introducing constraints to bound the reward function based on the precomputed reward potentials. Experimentally, we show that our algorithm efficiently computes reward potentials for learned NN models, and that the overhead of computing reward potentials is justified by the overall strengthening of the underlying MILP model for the task of planning over long horizons., Comment: To appear in the proceedings of the 25th International Conference on Principles and Practice of Constraint Programming

In this paper, we introduce the Action Schema Network (ASNet): a neural network architecture for learning generalised policies for probabilistic planning problems. By mimicking the relational structure of planning problems, ASNets are able to adopt a weight-sharing scheme which allows the network to be applied to any problem from a given planning domain. This allows the cost of training the network to be amortised over all problems in that domain. Further, we propose a training method which balances exploration and supervised training on small problems to produce a policy which remains robust when evaluated on larger problems. In experiments, we show that ASNet's learning capability allows it to significantly outperform traditional non-learning planners in several challenging domains., Comment: Accepted to AAAI 2018

Markov decision processes (MDPs) are the standard formalism for modelling sequential decision making in stochastic environments. Policy synthesis addresses the problem of how to control or limit the decisions an agent makes so that a given specification is met. In this paper we consider PCTL*, the probabilistic counterpart of CTL*, as the specification language. Because in general the policy synthesis problem for PCTL* is undecidable, we restrict to policies whose execution history memory is finitely bounded a priori. Surprisingly, no algorithm for policy synthesis for this natural and expressive framework has been developed so far. We close this gap and describe a tableau-based algorithm that, given an MDP and a PCTL* specification, derives in a non-deterministic way a system of (possibly nonlinear) equalities and inequalities. The solutions of this system, if any, describe the desired (stochastic) policies. Our main result in this paper is the correctness of our method, i.e., soundness, completeness and termination., Comment: This is a long version of a conference paper published at TABLEAUX 2017. It contains proofs of the main results and fixes a bug. See the footnote on page 1 for details

In this paper we look into the problem of planning over hybrid domains, where change can be both discrete and instantaneous, or continuous over time. In addition, it is required that each state on the trajectory induced by the execution of plans complies with a given set of global constraints. We approach the computation of plans for such domains as the problem of searching over a deterministic state model. In this model, some of the successor states are obtained by solving numerically the so-called initial value problem over a set of ordinary differential equations (ODE) given by the current plan prefix. These equations hold over time intervals whose duration is determined dynamically, according to whether zero crossing events take place for a set of invariant conditions. The resulting planner, FS+, incorporates these features together with effective heuristic guidance. FS+ does not impose any of the syntactic restrictions on process effects often found on the existing literature on Hybrid Planning. A key concept of our approach is that a clear separation is struck between planning and simulation time steps. The former is the time allowed to observe the evolution of a given dynamical system before committing to a future course of action, whilst the later is part of the model of the environment. FS+ is shown to be a robust planner over a diverse set of hybrid domains, taken from the existing literature on hybrid planning and systems., Comment: 17 pages

Smart devices, storage and other distributed technologies have the potential to greatly improve the utilisation of network infrastructure and renewable generation. Decentralised control of these technologies overcomes many scalability and privacy concerns, but in general still requires the underlying problem to be convex in order to guarantee convergence to a global optimum. Considering that AC power flows are non-convex in nature, and the operation of household devices often requires discrete decisions, there has been uncertainty surrounding the use of distributed methods in a realistic setting. This paper extends prior work on the alternating direction method of multipliers (ADMM) for solving the dynamic optimal power flow (D-OPF) problem. We utilise more realistic line and load models, and introduce a two-stage approach to managing discrete decisions and uncertainty. Our experiments on a suburb-sized microgrid show that this approach provides near optimal results, in a time that is fast enough for receding horizon control. This work brings distributed control of smart-grid technologies closer to reality., Comment: This work has been submitted to the IEEE for possible publication

This paper proposes an energy management technique for a consumer-to-grid system in smart grid. The benefit to consumers is made the primary concern to encourage consumers to participate voluntarily in energy trading with the central power station (CPS) in situations of energy deficiency. A novel system model motivating energy trading under the goal of social optimality is proposed. A single-leader multiple-follower Stackelberg game is then studied to model the interactions between the CPS and a number of energy consumers (ECs), and to find optimal distributed solutions for the optimization problem based on the system model. The CPS is considered as a leader seeking to minimize its total cost of buying energy from the ECs, and the ECs are the followers who decide on how much energy they will sell to the CPS for maximizing their utilities. It is shown that the game, which can be implemented distributedly, possesses a socially optimal solution, in which the benefits-sum to all consumers is maximized, as the total cost to the CPS is minimized. Numerical analysis confirms the effectiveness of the game., Comment: 10 pages, 8 figures. IEEE Transactions on Smart Grid, 2013

This paper explores an idea of demand-supply balance for smart grids in which consumers are expected to play a significant role. The main objective is to motivate the consumer, by maximizing their benefit both as a seller and a buyer, to trade their surplus energy with the grid so as to balance the demand at the peak hour. To that end, a Stackelberg game is proposed to capture the interactions between the grid and consumers, and it is shown analytically that optimal energy trading parameters that maximize customers utilities are obtained at the solution of the game. A novel distributed algorithm is proposed to reach the optimal solution of the game, and numerical examples are used to assess the properties and effectiveness of the proposed approach.

Integrating diagnosis and repair is particularly crucial when gaining sufficient information to discriminate between several candidate diagnoses requires carrying out some repair actions. A typical case is supply restoration in a faulty power distribution system. This problem, which is a major concern for electricity distributors, features partial observability, and stochastic repair actions which are more elaborate than simple replacement of components. This paper analyses the difficulties in applying existing work on integrating model-based diagnosis and repair and on planning in partially observable stochastic domains to this real-world problem, and describes the pragmatic approach we have retained so far., Comment: Appears in Proceedings of the Twelfth Conference on Uncertainty in Artificial Intelligence (UAI1996)

A popular approach to solving a decision process with non-Markovian rewards (NMRDP) is to exploit a compact representation of the reward function to automatically translate the NMRDP into an equivalent Markov decision process (MDP) amenable to our favorite MDP solution method. The contribution of this paper is a representation of non-Markovian reward functions and a translation into MDP aimed at making the best possible use of state-based anytime algorithms as the solution method. By explicitly constructing and exploring only parts of the state space, these algorithms are able to trade computation time for policy quality, and have proven quite effective in dealing with large MDPs. Our representation extends future linear temporal logic (FLTL) to express rewards. Our translation has the effect of embedding model-checking in the solution method. It results in an MDP of the minimal size achievable without stepping outside the anytime framework, and consequently in better policies by the deadline., Comment: Appears in Proceedings of the Eighteenth Conference on Uncertainty in Artificial Intelligence (UAI2002)

This paper examines a number of solution methods for decision processes with non-Markovian rewards (NMRDPs). They all exploit a temporal logic specification of the reward function to automatically translate the NMRDP into an equivalent Markov decision process (MDP) amenable to well-known MDP solution methods. They differ however in the representation of the target MDP and the class of MDP solution methods to which they are suited. As a result, they adopt different temporal logics and different translations. Unfortunately, no implementation of these methods nor experimental let alone comparative results have ever been reported. This paper is the first step towards filling this gap. We describe an integrated system for solving NMRDPs which implements these methods and several variants under a common interface; we use it to compare the various approaches and identify the problem features favoring one over the other., Comment: Appears in Proceedings of the Nineteenth Conference on Uncertainty in Artificial Intelligence (UAI2003)

We consider the problem of computing optimal generalised policies for relational Markov decision processes. We describe an approach combining some of the benefits of purely inductive techniques with those of symbolic dynamic programming methods. The latter reason about the optimal value function using first-order decision theoretic regression and formula rewriting, while the former, when provided with a suitable hypotheses language, are capable of generalising value functions or policies for small instances. Our idea is to use reasoning and in particular classical first-order regression to automatically generate a hypotheses language dedicated to the domain at hand, which is then used as input by an inductive solver. This approach avoids the more complex reasoning of symbolic dynamic programming while focusing the inductive solver's attention on concepts that are specifically relevant to the optimal value function for the domain considered., Comment: Appears in Proceedings of the Twentieth Conference on Uncertainty in Artificial Intelligence (UAI2004)