paper-with-me

Papers

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

2020-04-28 · Cameron Allen, Michael Katz, Tim Klinger, George Konidaris, Matthew Riemer, Gerald Tesauro

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.

📄 PDF Abstract BibTeX arXiv:2004.13242

Code (2)

camall3n/focused-macros 공식 구현
camall3n/skills-for-planning 공식 구현

Methods 이 논문이 사용한 방법론

Tanh Activation 설명 없음
Softmax The Softmax output function transforms a previous layer's output into a vector of probabilities. It is commonly used for multiclass classification. Given an input vector $x$…
LAMA 설명 없음

Similar Papers 제목 키워드 기반

MAGIC: Learning Macro-Actions for Online POMDP Planning

2020-11-07 · Yiyuan Lee, Panpan Cai, David Hsu

The partially observable Markov decision process (POMDP) is a principled general framework for robot decision making under uncertainty, but POMDP planning suffers from high computational complexity, when long-term planni…

Computational EfficiencyDecision MakingDecision Making Under Uncertainty

Mining useful Macro-actions in Planning

2018-10-22 · Sandra Castellanos-Paez, Damien Pellier, Humbert Fiorino, Sylvie Pesty

Planning has achieved significant progress in recent years. Among the various approaches to scale up plan synthesis, the use of macro-actions has been widely explored. As a first stage towards the development of a soluti…

Learning Macro-actions for State-Space Planning

2016-10-07 · Sandra Castellanos-Paez, Damien Pellier, Humbert Fiorino, Sylvie Pesty

Planning has achieved significant progress in recent years. Among the various approaches to scale up plan synthesis, the use of macro-actions has been widely explored. As a first stage towards the development of a soluti…

Monte Carlo Value Iteration with Macro-Actions

2011-12-01 · NeurIPS 2011 12 · Zhan Lim, Lee Sun, David Hsu

POMDP planning faces two major computational challenges: large state spaces and long planning horizons. The recently introduced Monte Carlo Value Iteration (MCVI) can tackle POMDPs with very large discrete state spaces o…

Belief-Dependent Macro-Action Discovery in POMDPs using the Value of Information

2020-12-01 · NeurIPS 2020 12 · Genevieve Flaspohler, Nicholas A. Roy, John W. Fisher III

This work introduces macro-action discovery using value-of-information (VoI) for robust and efficient planning in partially observable Markov decision processes (POMDPs). POMDPs are a powerful framework for planning unde…