Sciweavers

99 search results - page 6 / 20
» Software agents that learn through observation
Sort
View
ICML
1999
IEEE
16 years 2 months ago
Implicit Imitation in Multiagent Reinforcement Learning
Imitation is actively being studied as an effective means of learning in multi-agent environments. It allows an agent to learn how to act well (perhaps optimally) by passively obs...
Bob Price, Craig Boutilier
AI
2006
Springer
15 years 5 months ago
Satisfaction Equilibrium: Achieving Cooperation in Incomplete Information Games
So far, most equilibrium concepts in game theory require that the rewards and actions of the other agents are known and/or observed by all agents. However, in real life problems, a...
Stéphane Ross, Brahim Chaib-draa
ICEIS
2009
IEEE
15 years 8 months ago
AgEx: A Financial Market Simulation Tool for Software Agents
Many researchers in the software agent field use the financial domain as a test bed to develop adaptation, cooperation and learning skills of software agents. However, there are no...
Paulo André Lima de Castro, Jaime Sim&atild...
AGENTS
1997
Springer
15 years 5 months ago
Creatures: Artificial Life Autonomous Software Agents for Home Entertainment
This paper gives a technical description of Creatures, a commercial home-entertainment software package. Creatures provides a simulated environment in which exist a number of synt...
Stephen Grand, Dave Cliff, Anil Malhotra
ATAL
2004
Springer
15 years 6 months ago
Normative Agent Reasoning in Dynamic Societies
Several innovative software applications such as those required by ambient intelligence, the semantic grid, e-commerce and e-marketing, can be viewed as open societies of heteroge...
Fabiola López y López, Michael Luck,...