JOURNAL OF COMPUTERS (JCP)
ISSN : 1796-203X
Volume : 3    Issue : 9    Date : September 2008

Agent Learning in Relational Domains based on Logical MDPs with Negation
Song Zhiwei, Chen Xiaoping, and Cong Shuang
Page(s): 29-38
Full Text:
PDF (384 KB)


Abstract
In this paper, we propose a model named Logical Markov Decision Processes with Negation for
Relational Reinforcement Learning for applying Reinforcement Learning algorithms on the
relational domains with the states and actions in relational form. In the model, the logical negation
is represented explicitly, so that the abstract state space can be constructed from the goal state(s)
of a given task simply by applying a generating method and an expanding method, and each ground
state can be represented by one and only one abstract state. Prototype action is also introduced into
the model, so that the applicable abstract actions can be obtained automatically. Based on the
model, a model-freeΘ(λ)-learning algorithm is implemented to evaluate the state-action-
substitution value function. We also propose a state refinement method guided by two formal
definitions of self-loop degree and common characteristic of abstract states to construct the
abstract state space automatically by the agent itself rather than manually. The experiments show
that the agent can catch the core of the given task, and the final state space is intuitive.

Index Terms
Relational Reinforcement Learning, Logical MDPs with Negation, Θ(λ)-Learning, State Refinement