54 search results - page 1 / 11 » Convergence Results for Single-Step On-Policy Reinforcement-... |
ML
2000
ACM
13 years 9 months ago
2000
ACM
FUZZIEEE
2007
IEEE
14 years 3 months ago
2007
IEEE
— Reinforcement learning (RL) is a learning control paradigm that provides well-understood algorithms with good convergence and consistency properties. Unfortunately, these algor...
ICML
2004
IEEE
14 years 10 months ago
2004
IEEE
Synchronous reinforcement learning (RL) algorithms with linear function approximation are representable as inhomogeneous matrix iterations of a special form (Schoknecht & Merk...
ICML
2000
IEEE
14 years 10 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...
IAT
2007
IEEE
14 years 3 months ago
2007
IEEE
This paper proposes a mechanism of noise tolerance for reinforcement learning algorithms. An adaptive agent that employs reinforcement learning algorithms may receive and accumula...