46 search results - page 5 / 10 » Discretization of Continuous Action Spaces in Extensive-Form... |
97
Voted
ICANNGA
2007
Springer
15 years 4 months ago
2007
Springer
Reinforcement Learning (RL) is analyzed here as a tool for control system optimization. State and action spaces are assumed to be continuous. Time is assumed to be discrete, yet th...
91
Voted
AIIDE
2006
14 years 11 months ago
2006
Reinforcement learning is an effective machine learning paradigm in domains represented by compact and discrete state-action spaces. In high-dimensional and continuous domains, ti...
87
Voted
ATAL
2009
Springer
15 years 4 months ago
2009
Springer
Many problems of multiagent planning under uncertainty require distributed reasoning with continuous resources and resource limits. Decentralized Markov Decision Problems (Dec-MDP...
AAMAS
2007
Springer
15 years 4 months ago
2007
Springer
Abstract. Reinforcement learning (RL) is a widely used learning paradigm for adaptive agents. There exist several convergent and consistent RL algorithms which have been intensivel...
76
Voted
CDC
2008
IEEE
15 years 8 days ago
2008
IEEE
Abstract-- The aim of this paper is to address left invertibility for dynamical systems with inputs and outputs in discrete sets. We study systems that evolve in discrete time with...