Sciweavers

548 search results - page 3 / 110
» A New Way to Introduce Knowledge into Reinforcement Learning
Sort
View
ECAI
2008
Springer
13 years 8 months ago
Belief revision with reinforcement learning for interactive object recognition
From a conceptual point of view, belief revision and learning are quite similar. Both methods change the belief state of an intelligent agent by processing incoming information. Ho...
Thomas Leopold, Gabriele Kern-Isberner, Gabriele P...
ICCCI
2011
Springer
12 years 5 months ago
Evolving Equilibrium Policies for a Multiagent Reinforcement Learning Problem with State Attractors
Multiagent reinforcement learning problems are especially difficult because of their dynamism and the size of joint state space. In this paper a new benchmark problem is proposed, ...
Florin Leon
JACIII
2006
97views more  JACIII 2006»
13 years 6 months ago
Opposition-Based Reinforcement Learning
In this paper a method for image segmentation using an opposition-based reinforcement learning scheme is introduced. We use this agent-based approach to optimally find the appropri...
Hamid R. Tizhoosh
ECIS
2004
13 years 7 months ago
Beyond Knowledge Management - Introducing a framework for Learning Management Systems
In the knowledge economy, a firm's intellectual capital represents the only sustainable source of competitive advantage. Intellectual capital manifests itself, predominantly,...
Audrey Dunne, Tom Butler
AAAI
2006
13 years 7 months ago
Using Homomorphisms to Transfer Options across Continuous Reinforcement Learning Domains
We examine the problem of Transfer in Reinforcement Learning and present a method to utilize knowledge acquired in one Markov Decision Process (MDP) to bootstrap learning in a mor...
Vishal Soni, Satinder P. Singh