81 search results - page 4 / 17 » The Optimal Reward Baseline for Gradient-Based Reinforcement... |
ICML
2007
IEEE
14 years 8 months ago
2007
IEEE
Many robot control problems of practical importance, including operational space control, can be reformulated as immediate reward reinforcement learning problems. However, few of ...
KI
2007
Springer
14 years 1 months ago
2007
Springer
In this paper, we show how reinforcement learning can be applied to real robots to achieve optimal robot behavior. As example, we enable an autonomous soccer robot to learn interce...
ICML
2008
IEEE
14 years 8 months ago
2008
IEEE
We describe an algorithm for learning in the presence of multiple criteria. Our technique generalizes previous approaches in that it can learn optimal policies for all linear pref...
EUROCAST
2007
Springer
14 years 1 months ago
2007
Springer
Abstract a paradigm of modern Machine Learning (ML) which uses rewards and punishments to guide the learning process. One of the central ideas of RL is learning by “direct-online...
IJCAI
2001
13 years 9 months ago
2001
R-max is a very simple model-based reinforcement learning algorithm which can attain near-optimal average reward in polynomial time. In R-max, the agent always maintains a complet...