Guiding Inference Through Relational Reinforcement Learning

13 years 10 months ago

Download cll.stanford.edu

Abstract. Reasoning plays a central role in intelligent systems that operate in complex situations that involve time constraints. In this paper, we present the Adaptive Logic Interpreter, a reasoning system that acquires a controlled inference strategy adapted to the scenario at hand, using a variation on relational reinforcement learning. Employing this inference mechanism in a reactive agent architecture lets the agent focus its reasoning on the most rewarding parts of its knowledge base and hence perform better under time and computational resource constraints. We present experiments that demonstrate the beneﬁts of this approach to reasoning in reactive agents, then discuss related work and directions for future research.

Nima Asgharbeygi, Negin Nejati, Pat Langley, Sachi

Real-time Traffic

Controlled Inference Strategy | ILP 2005 | Reactive Agents | Reasoning |

claim paper

» Guiding Inference with Policy Search Reinforcement Learning

» Transfer Learning in Reinforcement Learning Problems Through Partial Policy Recycling

» Learning from human teachers with Socially Guided Exploration

» Guiding exploration by preexisting knowledge without modifying reward

» The asymptotic equipartition property in reinforcement learning and its relation to return...

» Bayesian Policy Search for MultiAgent Role Discovery

» Efficient multiagent reinforcement learning through automated supervision

» Routing automated guided vehicles in container terminals through the Qlearning technique

Post Info
More Details (n/a)

Added	27 Jun 2010
Updated	27 Jun 2010
Type	Conference
Year	2005
Where	ILP
Authors	Nima Asgharbeygi, Negin Nejati, Pat Langley, Sachiyo Arai

Comments (0)

Sciweavers

Guiding Inference Through Relational Reinforcement Learning

Controlled Inference Strategy | ILP 2005 | Reactive Agents | Reasoning |

Explore & Download

Productivity Tools

Document Tools

Image Tools

Sciweavers