Published on Fri Oct 19 2012

Symbolic Generalization for On-line Planning

Zhengzhu Feng, Eric A. Hansen, Shlomo Zilberstein

Symbolic representations have been used successfully in off-line planning algorithms for Markov decision processes. We show that they can also improve the performance of on-line planners. We introduce Symbolic Real-Time Dynamic Programming.

0
0
0
Abstract

Symbolic representations have been used successfully in off-line planning algorithms for Markov decision processes. We show that they can also improve the performance of on-line planners. In addition to reducing computation time, symbolic generalization can reduce the amount of costly real-world interactions required for convergence. We introduce Symbolic Real-Time Dynamic Programming (or sRTDP), an extension of RTDP. After each step of on-line interaction with an environment, sRTDP uses symbolic model-checking techniques to generalizes its experience by updating a group of states rather than a single state. We examine two heuristic approaches to dynamic grouping of states and show that they accelerate the planning process significantly in terms of both CPU time and the number of steps of interaction with the environment.

Thu Dec 24 2020
Artificial Intelligence
SPOTTER: Extending Symbolic Planning Operators through Targeted Reinforcement Learning
Symbolic planning models allow decision-making agents to sequence actions in arbitrary ways. Reinforcement learning (RL) approaches do not require such models. RL approaches tend to require millions of episodes of experience and often learn policies that are not easily transferable to other tasks.
0
0
0
Thu Jan 16 2014
Artificial Intelligence
Automatic Induction of Bellman-Error Features for Probabilistic Planning
Domain-specific features are important in representing problem structure through out machine learning and decision-theoretic planning. Successful applications in real-world domains often require featurescrafted by human experts. Here, we propose automatic processes for learning useful domain-specific feature sets with little or no human intervention.
0
0
0
Tue May 28 2019
Artificial Intelligence
Learning Portable Representations for High-Level Planning
We present a framework for autonomously learning a portable representation that describes a collection of low-level continuous environments. We show that these abstract representations can be learned in a task-independent egocentric space specific to the agent.
0
0
0
Thu Jan 23 2014
Artificial Intelligence
Online Speedup Learning for Optimal Planning
Domain-independent planning is one of the foundational areas in the field of Artificial Intelligence. The objective is to find a sequence of actions, that is, a plan, that transforms the initial world state into a goal state. We present a novel method that reduces the cost of combining admissible heuristics for optimal planning.
0
0
0
Wed Jan 04 2017
Artificial Intelligence
Stochastic Planning and Lifted Inference
Lifted probabilistic inference and symbolic dynamic programming were introduced around the same time as algorithmic efforts to use abstraction in stochastic systems. These ideas evolved into two distinct lines of research, each supported by a rich literature.
0
0
0
Sun Jun 26 2011
Artificial Intelligence
Planning Through Stochastic Local Search and Temporal Action Graphs in LPG
We present some techniques for planning in domains specified with the recent standard language PDDL2.1. These techniques are implemented in LPG, a domain-independent planner that took part in the 3rd International Planning Competition (IPC)
0
0
0