Related papers: Macro-FF: Improving AI Planning with Automatically…
Industry 4.0 proposes the integration of artificial intelligence (AI) into manufacturing and other industries to create smart collaborative systems which enhance efficiency. The aim of this paper is to develop a flexible and adaptive…
Developing autonomous agents for web-based tasks is a core challenge in AI. While Large Language Model (LLM) agents can interpret complex user requests, they often operate as black boxes, making it difficult to diagnose why they fail or how…
Sequential decision making, commonly formalized as optimization of a Markov Decision Process, is a key challenge in artificial intelligence. Two successful approaches to MDP optimization are reinforcement learning and planning, which both…
Standard planners for sequential decision making (including Monte Carlo planning, tree search, dynamic programming, etc.) are constrained by an implicit sequential planning assumption: The order in which a plan is constructed is the same in…
Scientific discovery concerns finding patterns in data and creating insightful hypotheses that explain these patterns. Traditionally, this process required human ingenuity, but with the galloping advances in artificial intelligence (AI) it…
Landmarks have long played a pivotal role in automated planning, serving as crucial elements for improving the planning algorithms. The main limitation of classical landmark extraction methods is their sensitivity to specific planning…
Prior work on generating explanations in a planning and decision-making context has focused on providing the rationale behind an AI agent's decision making. While these methods provide the right explanations from the explainer's…
Discovering useful temporal abstractions, in the form of options, is widely thought to be key to applying reinforcement learning and planning to increasingly complex domains. Building on the empirical success of the Expert Iteration…
Recent studies have shown that carefully designed workflows coordinating large language models(LLMs) significantly enhance task-solving capabilities compared to using a single model. While an increasing number of works focus on autonomous…
Automated planning is a form of declarative problem solving which has recently drawn attention from the machine learning (ML) community. ML has been applied to planning either as a way to test `reasoning capabilities' of architectures, or…
Methods for learning and planning in sequential decision problems often assume the learner is aware of all possible states and actions in advance. This assumption is sometimes untenable. In this paper, we give a method to learn factored…
Reinforcement learning (RL) involves sequential decision making in uncertain environments. The aim of the decision-making agent is to maximize the benefit of acting in its environment over an extended period of time. Finding an optimal…
We study the iterative refinement of path planning for multiple robots, known as multi-agent pathfinding (MAPF). Given a graph, agents, their initial locations, and destinations, a solution of MAPF is a set of paths without collisions.…
Various works have utilized deep learning to address the query optimization problem in database system. They either learn to construct plans from scratch in a bottom-up manner or steer the plan generation behavior of traditional optimizer…
Domain-independent probabilistic planners input an MDP description in a factored representation language such as PPDDL or RDDL, and exploit the specifics of the representation for faster planning. Traditional algorithms operate on each…
Recent studies have explored integrating Large Language Models (LLMs) with search engines to leverage both the LLMs' internal pre-trained knowledge and external information. Specially, reinforcement learning (RL) has emerged as a promising…
In a multi-agent pathfinding (MAPF) problem, agents need to navigate from their start to their goal locations without colliding into each other. There are various MAPF algorithms, including Windowed Hierarchical Cooperative A*, Flow…
Many autonomous driving motion planners generate trajectories by optimizing a reward/cost functional. Designing and tuning a high-performance reward/cost functional for Level-4 autonomous driving vehicles with exposure to different driving…
Optimizing the parallel training of large models requires exploring intra-operator parallelism plans for a computation graph that typically contains tens of thousands of primitive operators. While the optimization of parallel data…
This paper presents a sampling-based motion planning framework that leverages the geometry of obstacles in a workspace as well as prior experiences from motion planning problems. Previous studies have demonstrated the benefits of utilizing…