Learning by Demonstration in Repeated Stochastic Games
Posted on07/06/2018
Despite much research in recent years, newly created multiagent learning (MAL) algorithms continue to have one or more fatal weaknesses. These weaknesses... Read More
Hierarchical POMDP Controller Optimization by Likelihood Maximization
Posted on23/07/2008
Planning can often be simplified by decomposing the task into smaller tasks arranged hierarchically. Charlin et al. [4] recently showed that the... Read More
Automated Hierarchy Discovery for Planning in Partially Observable Environments
Posted on23/12/2006
Planning in partially observable domains is a notoriously difficult problem. However, in many real-world scenarios, planning can be simplified by decomposing the... Read More