Efficient Black-Box Planning Using Macro-Actions with Focused Effects

• URL: http://arxiv.org/abs/2004.13242v3
• Date: Wed, 23 Jun 2021 19:38:24 GMT
• Title: Efficient Black-Box Planning Using Macro-Actions with Focused Effects
• Authors: Cameron Allen, Michael Katz, Tim Klinger, George Konidaris, Matthew Riemer, Gerald Tesauro
• Abstract summary: Heuristics can make search more efficient, but goal-awares for black-box planning. We show how to overcome this limitation by discovering macro-actions that make the goal-count more accurate.
• Score: 35.688161278362735
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: The difficulty of deterministic planning increases exponentially with search-tree depth. Black-box planning presents an even greater challenge, since planners must operate without an explicit model of the domain. Heuristics can make search more efficient, but goal-aware heuristics for black-box planning usually rely on goal counting, which is often quite uninformative. In this work, we show how to overcome this limitation by discovering macro-actions that make the goal-count heuristic more accurate. Our approach searches for macro-actions with focused effects (i.e. macros that modify only a small number of state variables), which align well with the assumptions made by the goal-count heuristic. Focused macros dramatically improve black-box planning efficiency across a wide range of planning domains, sometimes beating even state-of-the-art planners with access to a full domain model.

Related papers

• Meta-learning how to Share Credit among Macro-Actions [15.3064603135039]
  We argue that the difficulty stems from the trade-offs between reducing the average number of decisions per episode versus increasing the size of the action space.<n>We propose a novel regularization term that exploits the relationship between actions and macro-actions to improve the credit assignment mechanism.<n>Our results show significant improvements over the Rainbow-DQN baseline in all environments.
  arXiv  Detail & Related papers  (2025-06-16T16:52:49Z)
• Efficient Robotic Policy Learning via Latent Space Backward Planning [17.770562202624962]
  Current robotic planning methods often rely on predicting multi-frame images with full pixel details.<n>We propose a Latent Space Backward Planning scheme (LBP), which begins by grounding the task into final latent goals.<n>We show that LBP outperforms existing fine-grained and forward planning methods, achieving SOTA performance.
  arXiv  Detail & Related papers  (2025-05-11T06:13:51Z)
• Tree-Planner: Efficient Close-loop Task Planning with Large Language Models [63.06270302774049]
  Tree-Planner reframes task planning with Large Language Models into three distinct phases. Tree-Planner achieves state-of-the-art performance while maintaining high efficiency.
  arXiv  Detail & Related papers  (2023-10-12T17:59:50Z)
• AlphaBlock: Embodied Finetuning for Vision-Language Reasoning in Robot Manipulation [50.737355245505334]
  We propose a novel framework for learning high-level cognitive capabilities in robot manipulation tasks. The resulting dataset AlphaBlock consists of 35 comprehensive high-level tasks of multi-step text plans and paired observation.
  arXiv  Detail & Related papers  (2023-05-30T09:54:20Z)
• Online Tool Selection with Learned Grasp Prediction Models [15.915410623440875]
  Deep learning-based grasp prediction models have become an industry standard for robotic bin-picking systems. To maximize pick success, production environments are often equipped with several end-effector tools that can be swapped on-the-fly, based on the target object. We show how to choose the order of grasps to perform, and corresponding tool-change actions, to improve system throughput.
  arXiv  Detail & Related papers  (2023-02-15T20:52:38Z)
• Bayesian Optimization for Macro Placement [48.55456716632735]
  We develop a novel approach to macro placement using Bayesian optimization (BO) over sequence pairs. BO is a machine learning technique that uses a probabilistic surrogate model and an acquisition function. We demonstrate our algorithm on the fixed-outline macro placement problem with the half-perimeter wire length objective.
  arXiv  Detail & Related papers  (2022-07-18T06:17:06Z)
• Multi-Target Active Object Tracking with Monte Carlo Tree Search and Target Motion Modeling [126.26121580486289]
  In this work, we are dedicated to multi-target active object tracking (AOT), where there are multiple targets as well as multiple cameras in the environment. The goal is maximize the overall target coverage of all cameras. We establish a multi-target 2D environment to simulate the sports games, and experimental results demonstrate that our method can effectively improve the target coverage.
  arXiv  Detail & Related papers  (2022-05-07T05:08:15Z)
• Symbolic Search for Optimal Planning with Expressive Extensions [4.36572039512405]
  Some properties of a planning problem at hand require an expressive extension of the standard classical planning formalism to capture and model them. We study planning with axioms, planning with state-dependent action costs, oversubscription planning, and top-k planning.
  arXiv  Detail & Related papers  (2022-04-01T08:41:06Z)
• MAGIC: Learning Macro-Actions for Online POMDP Planning [14.156697390568617]
  MAGIC learns a macro-action generator end-to-end, using an online planner's performance as the feedback. We evaluate MAGIC on several long-horizon planning tasks both in simulation and on a real robot.
  arXiv  Detail & Related papers  (2020-11-07T17:18:45Z)
• Planning with Learned Object Importance in Large Problem Instances using Graph Neural Networks [28.488201307961624]
  Real-world planning problems often involve hundreds or even thousands of objects. We propose a graph neural network architecture for predicting object importance in a single inference pass. Our approach treats the planner and transition model as black boxes, and can be used with any off-the-shelf planner.
  arXiv  Detail & Related papers  (2020-09-11T18:55:08Z)
• Long-Horizon Visual Planning with Goal-Conditioned Hierarchical Predictors [124.30562402952319]
  The ability to predict and plan into the future is fundamental for agents acting in the world. Current learning approaches for visual prediction and planning fail on long-horizon tasks. We propose a framework for visual prediction and planning that is able to overcome both of these limitations.
  arXiv  Detail & Related papers  (2020-06-23T17:58:56Z)

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.