1236 search results - page 174 / 248 » Opposition-Based Reinforcement Learning |
AGI
2008
13 years 11 months ago
2008
In order to claim fully general intelligence in an autonomous agent, the ability to learn is one of the most central capabilities. Classical machine learning techniques have had ma...
IJCNN
2008
IEEE
14 years 4 months ago
2008
IEEE
— When an agent observes its environment, there are two important characteristics of the perceived information. One is the relevance of information and the other is redundancy. T...
AIIDE
2008
14 years 10 days ago
2008
We introduce the ALeRT (Action-dependent Learning Rates with Trends) algorithm that makes two modifications to the learning rate and one change to the exploration rate of traditio...
ICML
2000
IEEE
14 years 10 months ago
2000
IEEE
Eligibility traces have been shown to speed reinforcement learning, to make it more robust to hidden states, and to provide a link between Monte Carlo and temporal-difference meth...
ECML
2004
Springer
14 years 3 months ago
2004
Springer
Abstract. We present first experiments using Support Vector Regression as function approximator for an on-line, sarsa-like reinforcement learner. To overcome the batch nature of S...