1233 search results - page 174 / 247 » Feudal Reinforcement Learning |
ECML
2006
Springer
13 years 12 months 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...
NIPS
2007
13 years 9 months ago
2007
We present four new reinforcement learning algorithms based on actor-critic and natural-gradient ideas, and provide their convergence proofs. Actor-critic reinforcement learning m...
ICML
2009
IEEE
14 years 9 months ago
2009
IEEE
In this paper we introduce the first algorithms for efficiently learning a simulation policy for Monte-Carlo search. Our main idea is to optimise the balance of a simulation polic...
ICML
2001
IEEE
14 years 9 months ago
2001
IEEE
Direct policy search is a practical way to solve reinforcement learning problems involving continuous state and action spaces. The goal becomes finding policy parameters that maxi...
ECML
2007
Springer
14 years 2 months ago
2007
Springer
We present Policy Gradient Actor-Critic (PGAC), a new model-free Reinforcement Learning (RL) method for creating limited-memory stochastic policies for Partially Observable Markov ...