4 search results - page 1 / 1 » Multiagent Transfer Learning via Assignment-Based Decomposit... |
ICMLA
2009
13 years 2 months ago
2009
We describe a system that successfully transfers value function knowledge across multiple subdomains of realtime strategy games in the context of multiagent reinforcement learning....
ATAL
2009
Springer
13 years 11 months ago
2009
Springer
We consider the setting of multiple collaborative agents trying to complete a set of tasks as assigned by a centralized controller. We propose a scalable method called“Assignmen...
AAAI
2010
13 years 6 months ago
2010
Bayesian inference is an appealing approach for leveraging prior knowledge in reinforcement learning (RL). In this paper we describe an algorithm for discovering different classes...
ATAL
2010
Springer
13 years 5 months ago
2010
Springer
We introduce the novel problem of inter-robot transfer learning for perceptual classification of objects, where multiple heterogeneous robots communicate and transfer learned obje...