We analyse the cost of using LLMs for planning and highlight that recent trends are profoundly uneconomical. We propose a significantly more efficient approach and argue for a responsible use of compute resources; urging research community to investigate LLM-based approaches that upholds efficiency.
The ability to generate multiple plans is central to using planning in real-life applications. Top-quality planners generate sets of such top-cost plans, allowing flexibility in determining equivalent ones. In terms of the order between actions in a plan, the literature only considers two extremes -- either all orders are important, making each plan unique, or all orders are unimportant, treating two plans differing only in the order of actions as equivalent. To allow flexibility in selecting important orders, we propose specifying a subset of actions the orders between which are important, interpolating between the top-quality and unordered top-quality planning problems. We explore the ways of adapting partial order reduction search pruning techniques to address this new computational problem and present experimental evaluations demonstrating the benefits of exploiting such techniques in this setting.
The growing utilization of planning tools in practical scenarios has sparked an interest in generating multiple high-quality plans. Consequently, a range of computational problems under the general umbrella of top-quality planning were introduced over a short time period, each with its own definition. In this work, we show that the existing definitions can be unified into one, based on a dominance relation. The different computational problems, therefore, simply correspond to different dominance relations. Given the unified definition, we can now certify the top-quality of the solutions, leveraging existing certification of unsolvability and optimality. We show that task transformations found in the existing literature can be employed for the efficient certification of various top-quality planning problems and propose a novel transformation to efficiently certify loopless top-quality planning.
AI planning and Reinforcement Learning (RL) both solve sequential decision-making problems under the different formulations. AI Planning requires operator models, but then allows efficient plan generation. RL requires no operator model, instead learns a policy to guide an agent to high reward states. Planning can be brittle in the face of noise whereas RL is more tolerant. However, RL requires a large number of training examples to learn the policy. In this work, we aim to bring AI planning and RL closer by showing that a suitably defined planning model can be used to improve the efficiency of RL. Specifically, we show that the options in the hierarchical RL can be derived from a planning task and integrate planning and RL algorithms for training option policy functions. Our experiments demonstrate an improved sample efficiency on a variety of RL environments over the previous state-of-the-art.
Recent advances in reinforcement learning (RL) have led to a growing interest in applying RL to classical planning domains or applying classical planning methods to some complex RL domains. However, the long-horizon goal-based problems found in classical planning lead to sparse rewards for RL, making direct application inefficient. In this paper, we propose to leverage domain-independent heuristic functions commonly used in the classical planning literature to improve the sample efficiency of RL. These classical heuristics act as dense reward generators to alleviate the sparse-rewards issue and enable our RL agent to learn domain-specific value functions as residuals on these heuristics, making learning easier. Correct application of this technique requires consolidating the discounted metric used in RL and the non-discounted metric used in heuristics. We implement the value functions using Neural Logic Machines, a neural network architecture designed for grounded first-order logic inputs. We demonstrate on several classical planning domains that using classical heuristics for RL allows for good sample efficiency compared to sparse-reward RL. We further show that our learned value functions generalize to novel problem instances in the same domain.
In this paper, we address the knowledge engineering problems for hypothesis generation motivated by applications that require timely exploration of hypotheses under unreliable observations. We looked at two applications: malware detection and intensive care delivery. In intensive care, the goal is to generate plausible hypotheses about the condition of the patient from clinical observations and further refine these hypotheses to create a recovery plan for the patient. Similarly, preventing malware spread within a corporate network involves generating hypotheses from network traffic data and selecting preventive actions. To this end, building on the already established characterization and use of AI planning for similar problems, we propose use of planning for the hypothesis generation problem. However, to deal with uncertainty, incomplete model description and unreliable observations, we need to use a planner capable of generating multiple high-quality plans. To capture the model description we propose a language called LTS++ and a web-based tool that enables the specification of the LTS++ model and a set of observations. We also proposed a 9-step process that helps provide guidance to the domain expert in specifying the LTS++ model. The hypotheses are then generated by running a planner on the translated LTS++ model and the provided trace. The hypotheses can be visualized and shown to the analyst or can be further investigated automatically.
In this paper, we address the problem of generating preferred plans by combining the procedural control knowledge specified by Hierarchical Task Networks (HTNs) with rich qualitative user preferences. The outcome of our work is a language for specifyin user preferences, tailored to HTN planning, together with a provably optimal preference-based planner, HTNPLAN, that is implemented as an extension of SHOP2. To compute preferred plans, we propose an approach based on forward-chaining heuristic search. Our heuristic uses an admissible evaluation function measuring the satisfaction of preferences over partial plans. Our empirical evaluation demonstrates the effectiveness of our HTNPLAN heuristics. We prove our approach sound and optimal with respect to the plans it generates by appealing to a situation calculus semantics of our preference language and of HTN planning. While our implementation builds on SHOP2, the language and techniques proposed here are relevant to a broad range of HTN planners.