D-RR-QL - Historial de revisiones

Bortx en 14:05 13 abr 2015

2015-04-13T14:05:18Z

← Revisión anterior		Revisión del 16:05 13 abr 2015
Línea 7:		Línea 7:
	:Plos-One		:Plos-One

	~~[[media~~:~~D-RR-QL_hose-transportation-experiments~~.~~zip\|~~D-RR-QL ~~source code]]~~		http://github.com/borjafdezgauna/D-RR-QL-PlosONE

Bortx en 18:01 24 oct 2014

2014-10-24T18:01:55Z

← Revisión anterior		Revisión del 20:01 24 oct 2014
Línea 6:		Línea 6:
	:Borja Fernandez-Gauna, Ismael Etxeberria-Agiriano and Manuel Graña		:Borja Fernandez-Gauna, Ismael Etxeberria-Agiriano and Manuel Graña
	:Plos-One		:Plos-One

			[[media:D-RR-QL_hose-transportation-experiments.zip\|D-RR-QL source code]]

Bortx en 16:48 24 oct 2014

2014-10-24T16:48:44Z

← Revisión anterior		Revisión del 18:48 24 oct 2014
Línea 3:		Línea 3:
	The main advantage of D-RR-QL is that it allows each agent to use Modular State-Action Vetoes, which is a technique that allows RL agents to boost their exploration efficiency when approaching over-constrained systems, such as Linked Multicomponent Robotic Systems. The following source-code was used in the experiments of the following paper:		The main advantage of D-RR-QL is that it allows each agent to use Modular State-Action Vetoes, which is a technique that allows RL agents to boost their exploration efficiency when approaching over-constrained systems, such as Linked Multicomponent Robotic Systems. The following source-code was used in the experiments of the following paper:

	::"Learning Multirobot Hose Transportation and Deployment by Round-Robin Distributed Q-Learning"		;"Learning Multirobot Hose Transportation and Deployment by Round-Robin Distributed Q-Learning"
	:Borja Fernandez-Gauna, Ismael Etxeberria-Agiriano and Manuel Graña		:Borja Fernandez-Gauna, Ismael Etxeberria-Agiriano and Manuel Graña
	:Plos-One		:Plos-One

Bortx en 09:27 24 oct 2014

2014-10-24T09:27:02Z

← Revisión anterior		Revisión del 11:27 24 oct 2014
Línea 3:		Línea 3:
	The main advantage of D-RR-QL is that it allows each agent to use Modular State-Action Vetoes, which is a technique that allows RL agents to boost their exploration efficiency when approaching over-constrained systems, such as Linked Multicomponent Robotic Systems. The following source-code was used in the experiments of the following paper:		The main advantage of D-RR-QL is that it allows each agent to use Modular State-Action Vetoes, which is a technique that allows RL agents to boost their exploration efficiency when approaching over-constrained systems, such as Linked Multicomponent Robotic Systems. The following source-code was used in the experiments of the following paper:

	"Learning Multirobot Hose Transportation and Deployment by Round-Robin Distributed Q-Learning"		::"Learning Multirobot Hose Transportation and Deployment by Round-Robin Distributed Q-Learning"
	Borja Fernandez-Gauna, Ismael Etxeberria-Agiriano and Manuel Graña		:Borja Fernandez-Gauna, Ismael Etxeberria-Agiriano and Manuel Graña
	Plos-One		:Plos-One

Bortx en 09:24 24 oct 2014

2014-10-24T09:24:26Z

← Revisión anterior		Revisión del 11:24 24 oct 2014
Línea 1:		Línea 1:
	Distributed Round-Robin Q-Learning (D-RR-QL) is a Reinforcement Learning algorithm that allows to approximate the optimal joint-policy of a multi-agent system in a two-step fashion. First, each agent learns in its own local state-action following a round-robin schedule, thus avoiding non-stationarity due to the rest of agents learning their own policies. Then a coordination procedure approximates the optimal joint-policy by a greedy selection procedure using message passing.		Distributed Round-Robin Q-Learning (D-RR-QL) is a Reinforcement Learning algorithm that allows to approximate the optimal joint-policy of a multi-agent system in a two-step fashion. First, each agent learns in its own local state-action following a round-robin schedule, thus avoiding non-stationarity due to the rest of agents learning their own policies. Then a coordination procedure approximates the optimal joint-policy by a greedy selection procedure using message passing.

	The main advantage of D-RR-QL is that it allows each agent to use Modular State-Action Vetoes, which is a technique that allows RL agents to boost their exploration efficiency when approaching over-constrained systems, such as Linked Multicomponent Robotic Systems. The code ~~that follows~~ was used in the experiments of the following paper:		The main advantage of D-RR-QL is that it allows each agent to use Modular State-Action Vetoes, which is a technique that allows RL agents to boost their exploration efficiency when approaching over-constrained systems, such as Linked Multicomponent Robotic Systems. The following source-code was used in the experiments of the following paper:

	"Learning Multirobot Hose Transportation and Deployment by Round-Robin Distributed Q-Learning"		"Learning Multirobot Hose Transportation and Deployment by Round-Robin Distributed Q-Learning"
	Borja Fernandez-Gauna, Ismael Etxeberria-Agiriano and Manuel Graña		Borja Fernandez-Gauna, Ismael Etxeberria-Agiriano and Manuel Graña
	Plos-One		Plos-One

Bortx: Página creada con «Distributed Round-Robin Q-Learning (D-RR-QL) is a Reinforcement Learning algorithm that allows to approximate the optimal joint-policy of a multi-agent system in a two-step...»

2014-10-24T09:23:29Z

Página creada con «Distributed Round-Robin Q-Learning (D-RR-QL) is a Reinforcement Learning algorithm that allows to approximate the optimal joint-policy of a multi-agent system in a two-step...»

Página nueva

Distributed Round-Robin Q-Learning (D-RR-QL) is a Reinforcement Learning algorithm that allows to approximate the optimal joint-policy of a multi-agent system in a two-step fashion. First, each agent learns in its own local state-action following a round-robin schedule, thus avoiding non-stationarity due to the rest of agents learning their own policies. Then a coordination procedure approximates the optimal joint-policy by a greedy selection procedure using message passing.

The main advantage of D-RR-QL is that it allows each agent to use Modular State-Action Vetoes, which is a technique that allows RL agents to boost their exploration efficiency when approaching over-constrained systems, such as Linked Multicomponent Robotic Systems. The code that follows was used in the experiments of the following paper:

"Learning Multirobot Hose Transportation and Deployment by Round-Robin Distributed Q-Learning"
Borja Fernandez-Gauna, Ismael Etxeberria-Agiriano and Manuel Graña
Plos-One