82 search results - page 3 / 17 » Practical Reinforcement Learning in Continuous Spaces |
NECO
2000
13 years 8 months ago
2000
NIPS
1996
13 years 10 months ago
1996
Dynamic Programming, Q-learning and other discrete Markov Decision Process solvers can be applied to continuous d-dimensional state-spaces by quantizing the state space into an arr...
ECML
2006
Springer
14 years 7 days ago
2006
Springer
We target the problem of closed-loop learning of control policies that map visual percepts to continuous actions. Our algorithm, called Reinforcement Learning of Joint Classes (RLJ...
ICML
2007
IEEE
14 years 9 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 ...
ICML
2004
IEEE
14 years 9 months ago
2004
IEEE
Reinforcement learning deals with learning optimal or near optimal policies while interacting with the environment. Application domains with many continuous variables are difficul...