43 search results - page 1 / 9 » The O.D.E. Method for Convergence of Stochastic Approximatio... |
SIAMCO
2000
13 years 5 months ago
2000
It is shown here that stability of the stochastic approximation algorithm is implied by the asymptotic stability of the origin for an associated ODE. This in turn implies convergen...
ICML
2000
IEEE
14 years 6 months ago
2000
IEEE
Stochastic games are a generalization of MDPs to multiple agents, and can be used as a framework for investigating multiagent learning. Hu and Wellman (1998) recently proposed a m...
ICML
1996
IEEE
13 years 9 months ago
1996
IEEE
This paper presents a direct reinforcement learning algorithm, called Finite-Element Reinforcement Learning, in the continuous case, i.e. continuous state-space and time. The eval...
AAAI
2000
13 years 6 months ago
2000
Reinforcement learning (RL) can be impractical for many high dimensional problems because of the computational cost of doing stochastic search in large state spaces. We propose a ...
NIPS
2007
13 years 6 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...