We contribute Policy Reuse as a technique to improve a reinforcement learning agent with guidance from past learned similar policies. Our method relies on using the past policies ...
The concepts of autonomous agent and multi-agent system appropriate levels of abstraction for the design, implementation and simulation of many complex, distributed computational s...
Michael Luck, Peter McBurney, Jorge Gonzalez-Palac...
Most of current machine vision systems suffer from a lack of flexibility to account for the high variability of unstructured environments. Here, as the state of the world evolves ...
Main stream approaches in distributed artificial intelligence (DAI) are essentially logic-based. Little has been reported to explore probabilistic approach in DAI. On the other han...
Multi-agent system(MAS) is a blooming research area, which exhibits a new paradigm for the design, modelling and implementation of complex systems. A significant amount of effort...
Mengqiu Wang, Mariusz Nowostawski, Martin K. Purvi...