Symbolic Generalization for On-line Planning

10/19/2012
by   Zhengzhu Feng, et al.
0

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.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
04/20/2018

PEORL: Integrating Symbolic Planning and Hierarchical Reinforcement Learning for Robust Decision-Making

Reinforcement learning and symbolic planning have both been used to buil...
research
12/23/2019

Towards Symbolic Factual Change in DEL

We extend symbolic model checking for Dynamic Epistemic Logic (DEL) with...
research
04/15/2021

Symbolic Time and Space Tradeoffs for Probabilistic Verification

We present a faster symbolic algorithm for the following central problem...
research
06/06/2017

Symbolic Multibody Methods for Real-Time Simulation of Railway Vehicles

In this work, recently developed state-of-the-art symbolic multibody met...
research
02/27/2013

Symbolic Probabilitistic Inference in Large BN2O Networks

A BN2O network is a two level belief net in which the parent interaction...
research
09/24/2021

A dynamic programming algorithm for informative measurements and near-optimal path-planning

An informative measurement is the most efficient way to gain information...
research
02/08/2023

Learning How to Infer Partial MDPs for In-Context Adaptation and Exploration

To generalize across tasks, an agent should acquire knowledge from past ...

Please sign up or login with your details

Forgot password? Click here to reset