A. Kagan, T. adn Agogino and D. Wolpert. Learning sequences of actions in collectives of autonomous agents. In Proceedings of Autonomous Agents and Multi-Agent Systems (AAMAS-2002. Home/Search Document Details and Download
Summary Related Articles Check |
This paper is cited in the following contexts:
COllective INtelligence with Sequences of Actions: Coordinating .. - Hoen, Bohte (2003) (3 citations) (Correct)
....proved to be very e#ective for learning these problems in a distributed system. In particular, the systems exhibited excellent scaling properties. Compared to optimal solutions, it is observed that a system like COIN becomes relatively better as the problem is scaled up [17] In recent work [10], the COIN framework has been applied to problems where di#erent single agent RL algorithms are traditionally tested: grid based world exploration games [10, 8] In this problem domain, agents move on a grid like world where their aim is to collect tokens representing localized rewards as ....
.... to optimal solutions, it is observed that a system like COIN becomes relatively better as the problem is scaled up [17] In recent work [10] the COIN framework has been applied to problems where di#erent single agent RL algorithms are traditionally tested: grid based world exploration games [10, 8]. In this problem domain, agents move on a grid like world where their aim is to collect tokens representing localized rewards as e#ciently as possible (e.g. 8] For a Multi Agent System, the challenge is to find sequences of actions for each individual agent such that their joint sequences of ....
[Article contains additional citation context not shown here]
K. Tumer, A. Agogino, and D. Wolpert. Learning sequences of actions in collectives of autonomous agents. In Autonomous Agents & Multiagent Systems, pages 378--385, part 1. ACM press, 2002.
COllective INtelligence with Sequences of Actions: Coordinating .. - Hoen, Bohte (2003) (3 citations) (Correct)
....proved to be very e#ective for learning these problems in a distributed system. In particular, the systems exhibited excellent scaling properties. Compared to optimal solutions, it is observed that a system like COIN becomes relatively better as the problem is scaled up [17] In recent work [10], the COIN framework has been applied to problems where di#erent single agent RL algorithms are traditionally tested: grid based world exploration games [10,8] In this problem domain, agents move on a grid like world where their aim is to collect tokens representing localized rewards as ....
.... to optimal solutions, it is observed that a system like COIN becomes relatively better as the problem is scaled up [17] In recent work [10] the COIN framework has been applied to problems where di#erent single agent RL algorithms are traditionally tested: grid based world exploration games [10,8]. In this problem domain, agents move on a grid like world where their aim is to collect tokens representing localized rewards as e#ciently as possible (e.g. 8] For a Multi Agent System, the challenge is to find sequences of actions for each individual agent such that their joint sequences of ....
[Article contains additional citation context not shown here]
K. Tumer, A. Agogino, and D. Wolpert. Learning sequences of actions in collectives of autonomous agents. In Autonomous Agents & Multiagent Systems, pages 378--385, part 1. ACM press, 2002.
Bidding with Decommitment in a Multi-Agent Transportation .. - Hoen, van Bragt.. (2002) (1 citation) (Correct)
....can also be useful for the transportation problem which is considered here. For example, the value of a load can increase when the truck, by transporting the extra load, can move cheaply to an area of the grid with a high density of depots. Another venue of research is in the line of COIN [31, 28], where the aim would be to modify the agents valuation function to let them more eiiciently cooperate as one company. Such refinements of the agent s valuation function form an interesting topic for further studies. There is obviously an incentive for a company to avoid competition between its ....
K. Tumer, A. Agogino, and D. Wolpert. Learning sequences of actions in collectives of autonomous agents. In Autonomous Agents 4 Multiagent Systems, pages 378-385, part 1. ACM press, 2002.
Bidding with Decommitment in a Multi-Agent Transportation .. - Hoen, van Bragt.. (2002) (1 citation) (Correct)
....can also be useful for the transportation problem which is considered here. For example, the value of a load can increase when the truck, by transporting the extra load, can move cheaply to an area of the grid with a high density of depots. Another venue of research is in the line of COIN [ 31, 28 ] , where the aim would be to modify the agents valuation function to let them more eciently cooperate as one company. Such re nements of the agent s valuation function form an interesting topic for further studies. There is obviously an incentive for a company to avoid competition between its ....
K. Tumer, A. Agogino, and D. Wolpert. Learning sequences of actions in collectives of autonomous agents. In Autonomous Agents & Multiagent Systems, pages 378-385, part 1. ACM press, 2002.
Unifying Temporal and Structural Credit Assignment Problems - Agogino, Tumer (2004) Self-citation (Tumer Agogino) (Correct)
No context found.
K. Tumer, A. Agogino, and D. Wolpert. Learning sequences of actions in collectives of autonomous agents. In Proceedings of the First International Joint Conference on Autonomous Agents and Multi-Agent Systems, pages 378--385, Bologna, Italy, July 2002.
Exploiting Multi-Agent Interactions - For Identifying The (2005) (Correct)
No context found.
A. Kagan, T. adn Agogino and D. Wolpert. Learning sequences of actions in collectives of autonomous agents. In Proceedings of Autonomous Agents and Multi-Agent Systems (AAMAS-2002.
TraderBots: A Market-Based Approach For Resource, Role, and.. - Dias, Stentz (2003) (Correct)
No context found.
Tumer, Kagan, Agogino, Adrian K., and Wolpert, David, "Learning sequences of actions in collectives of autonomous agents", First International Joint Conference on Autonomous Agents and Multi-Agent Systems (AAMAS), pp.378-385, 2002.
Multi-Agent Cooperation Using Trickle-Down Utility - McLean (2003) (Correct)
No context found.
Kagan Tumer, Adrian K. Agogino, and David H. Wolpert. "Learning Sequences of Actions in Collectives of Autonomous Agents". Proceedings of the First International Joint Conference on Autonomous Agents and Multiagent Systems. ACM Press, New York, NY, 1999.
Online articles have much greater impact More about CiteSeer.IST Add search form to your site Submit documents Feedback
CiteSeer.IST - Copyright Penn State and NEC