Title | ||
---|---|---|
Safe Inclusion of Information about Rates of Variation in a Reinforcement Learning Algorithm |
Abstract | ||
---|---|---|
There is a need to enhance reinforcement learning techniques by using prior knowledge built into the agent at its inception. The information crudeness upon which those algorithms operate may be interesting from a theoretical point of view, but large scale problems are made too difficult and unrealistic by considering the learning agent as a `tabula rasa'. Nonetheless,knowledge must be embedded in such a way that the structural, well-studied characteristics of the fundamental algorithms are maintained.A more general formulation of a classical reinforcement learning method is investigated in this article. It allows for a spreading of information derived from single updates towards a neighbourhood of the instantly visited state, and converges to optimality. We show how this new formulation can be used as a mechanism to safely embed prior knowledge about expected rates of variation of action values, and practical studies demonstrate an application of the proposed algorithm. |
Year | DOI | Venue |
---|---|---|
1998 | 10.1109/SBRN.1998.730985 | Belo Horizonte |
Keywords | Field | DocType |
practical study,expected rate,action value,general formulation,new formulation,reinforcement learning algorithm,fundamental algorithm,information crudeness,classical reinforcement,safe inclusion,large scale problem,prior knowledge,read only memory,dynamic programming,stochastic processes,intelligent control,cost function,knowledge representation,learning artificial intelligence,q learning,reinforcement learning,convergence,approximation theory | Intelligent control,Convergence (routing),Dynamic programming,Knowledge representation and reasoning,Computer science,Q-learning,Approximation theory,Artificial intelligence,Tabula rasa,Machine learning,Reinforcement learning | Conference |
ISBN | Citations | PageRank |
0-8186-8629-4 | 0 | 0.34 |
References | Authors | |
3 | 1 |
Name | Order | Citations | PageRank |
---|---|---|---|
Carlos H. C. Ribeiro | 1 | 169 | 34.25 |