Learning High-Level Planning from Text
S. R. K. Branavan, Nate Kushman, Tao Lei et al. · DSpace@MIT (Massachusetts Institute of Technology) · 2012
Comprehending action preconditions and ef-fects is an essential step in modeling the dy-namics of the world. In this paper, we ex-press the semantics of precondition relations extracted from text in terms of planning oper-ations. The challenge of modeling this con-nection is to ground language at the level of relations. This type of grounding enables us to create high-level plans based on language ab-stractions. Our model jointly learns to predict precondition relations from text and to per-form high-level planning guided by those rela-tions. We implement this idea in the reinforce-ment learning framework using feedback au-tomatically obtained from plan execution at-tempts. When applied to a complex virtual world and text describing that world, our rela-tion extraction technique performs on par with a supervised baseline, yielding an F-measure of 66 % compared to the baseline’s 65%. Ad-ditionally, we show that a high-level planner utilizing these extracted relations significantly outperforms a strong, text unaware baseline – successfully completing 80 % of planning tasks as compared to 69 % for the baseline.1 1
Cited by 52 works. Open-access PDF
Authors
References
- Reinforcement Learning: An Introduction
- Introduction to Reinforcement Learning
- Simple statistical gradient-following algorithms for connectionist reinforcement learning
- Making Large-Scale Support Vector Machine Learning Practical
- Policy Gradient Methods for Reinforcement Learning with Function Approximation
- Generating Typed Dependency Parses from Phrase Structure Parses
- Reinforcement Learning:
- The FF Planning System: Fast Plan Generation Through Heuristic Search
- PDDL2.1: An Extension to PDDL for Expressing Temporal Planning Domains
- Automated Planning: Theory and Practice