Goal Agnostic Planning using Maximum Likelihood Paths in Hypergraph World Models

• URL: http://arxiv.org/abs/2110.09442v1
• Date: Mon, 18 Oct 2021 16:22:33 GMT
• Title: Goal Agnostic Planning using Maximum Likelihood Paths in Hypergraph World Models
• Authors: Christopher Robinson
• Abstract summary: We present a hypergraph-based machine learning algorithm, a datastructure--driven maintenance method, and a planning algorithm based on a probabilistic application of Dijkstra's algorithm. We prove that the algorithm determines optimal solutions within the problem space, mathematically bound learning performance, and supply a mathematical model analyzing system state progression through time.
• Score: 1.370633147306388
• License: http://creativecommons.org/licenses/by-nc-nd/4.0/
• Abstract: In this paper, we present a hypergraph--based machine learning algorithm, a datastructure--driven maintenance method, and a planning algorithm based on a probabilistic application of Dijkstra's algorithm. Together, these form a goal agnostic automated planning engine for an autonomous learning agent which incorporates beneficial properties of both classical Machine Learning and traditional Artificial Intelligence. We prove that the algorithm determines optimal solutions within the problem space, mathematically bound learning performance, and supply a mathematical model analyzing system state progression through time yielding explicit predictions for learning curves, goal achievement rates, and response to abstractions and uncertainty. To validate performance, we exhibit results from applying the agent to three archetypal planning problems, including composite hierarchical domains, and highlight empirical findings which illustrate properties elucidated in the analysis.

Related papers

• AI-Aided Kalman Filters [65.35350122917914]
  The Kalman filter (KF) and its variants are among the most celebrated algorithms in signal processing. Recent developments illustrate the possibility of fusing deep neural networks (DNNs) with classic Kalman-type filtering. This article provides a tutorial-style overview of design approaches for incorporating AI in aiding KF-type algorithms.
  arXiv  Detail & Related papers  (2024-10-16T06:47:53Z)
• On Discriminative Probabilistic Modeling for Self-Supervised Representation Learning [85.75164588939185]
  We study the discriminative probabilistic modeling problem on a continuous domain for (multimodal) self-supervised representation learning. We conduct generalization error analysis to reveal the limitation of current InfoNCE-based contrastive loss for self-supervised representation learning.
  arXiv  Detail & Related papers  (2024-10-11T18:02:46Z)
• On the Markov Property of Neural Algorithmic Reasoning: Analyses and Methods [94.72563337153268]
  We present ForgetNet, which does not use historical embeddings and thus is consistent with the Markov nature of the tasks. We also introduce G-ForgetNet, which uses a gating mechanism to allow for the selective integration of historical embeddings. Our experiments, based on the CLRS-30 algorithmic reasoning benchmark, demonstrate that both ForgetNet and G-ForgetNet achieve better generalization capability than existing methods.
  arXiv  Detail & Related papers  (2024-03-07T22:35:22Z)
• Representation Learning with Multi-Step Inverse Kinematics: An Efficient and Optimal Approach to Rich-Observation RL [106.82295532402335]
  Existing reinforcement learning algorithms suffer from computational intractability, strong statistical assumptions, and suboptimal sample complexity. We provide the first computationally efficient algorithm that attains rate-optimal sample complexity with respect to the desired accuracy level. Our algorithm, MusIK, combines systematic exploration with representation learning based on multi-step inverse kinematics.
  arXiv  Detail & Related papers  (2023-04-12T14:51:47Z)
• Hierarchical Imitation Learning with Vector Quantized Models [77.67190661002691]
  We propose to use reinforcement learning to identify subgoals in expert trajectories. We build a vector-quantized generative model for the identified subgoals to perform subgoal-level planning. In experiments, the algorithm excels at solving complex, long-horizon decision-making problems outperforming state-of-the-art.
  arXiv  Detail & Related papers  (2023-01-30T15:04:39Z)
• Using Knowledge Graphs for Performance Prediction of Modular Optimization Algorithms [4.060078409841919]
  We build a performance prediction model using a knowledge graph embedding-based methodology. We show that a triple classification approach can correctly predict whether a given algorithm instance will be able to achieve a certain target precision.
  arXiv  Detail & Related papers  (2023-01-24T09:28:57Z)
• Latent Properties of Lifelong Learning Systems [59.50307752165016]
  We introduce an algorithm-agnostic explainable surrogate-modeling approach to estimate latent properties of lifelong learning algorithms. We validate the approach for estimating these properties via experiments on synthetic data.
  arXiv  Detail & Related papers  (2022-07-28T20:58:13Z)
• Learning Time-Varying Graphs from Online Data [39.21234914444073]
  This work proposes an algorithmic framework to learn time-varying graphs from online data. It renders it model-independent, i.e., it can be theoretically analyzed in its abstract formulation. We specialize the framework to three well-known graph learning models, namely, the Gaussian graphical model (GGM), the structural equation model (SEM), and the smoothness-based model (SBM)
  arXiv  Detail & Related papers  (2021-10-21T09:46:44Z)
• Compositional Reinforcement Learning from Logical Specifications [21.193231846438895]
  Recent approaches automatically generate a reward function from a given specification and use a suitable reinforcement learning algorithm to learn a policy. We develop a compositional learning approach, called DiRL, that interleaves high-level planning and reinforcement learning. Our approach then incorporates reinforcement learning to learn neural network policies for each edge (sub-task) within a Dijkstra-style planning algorithm to compute a high-level plan in the graph.
  arXiv  Detail & Related papers  (2021-06-25T22:54:28Z)
• Structured Prediction for CRiSP Inverse Kinematics Learning with Misspecified Robot Models [39.513301957826435]
  We introduce a structured prediction algorithm that combines a data-driven strategy with a forward kinematics function. The proposed approach ensures that predicted joint configurations are well within the robot's constraints.
  arXiv  Detail & Related papers  (2021-02-25T15:39:33Z)
• Learning to plan with uncertain topological maps [14.774543742438176]
  We train an agent to navigate in 3D environments using a hierarchical strategy including a graph based planner and a local policy. By performing an empirical analysis of our method in simulated photo-realistic 3D environments, we demonstrate that the inclusion of visual features in the learned neural planner outperforms classical symbolic solutions for graph based planning.
  arXiv  Detail & Related papers  (2020-07-10T09:28:30Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.