When an agent evolves in a partially observable environment, it has to deal with uncertainties when choosing its actions. An efficient model for such environments is to use partially observable Markov decision processes (POMDPs). Many algorithms have been developed for POMDPs. Some use an offline approach, learning a complete policy before the execution. Others use an online approach, construct...

Partially observable Markov decision processes (POMDPs) provide a principled framework for sequential planning in uncertain single agent settings. An extension of POMDPs to multiagent settings, called interactive POMDPs (I-POMDPs), replaces POMDP belief spaces with interactive hierarchical belief systems which represent an agent’s belief about the physical world, about beliefs of other agents, ...

Many people believe that language teaching is a neutral practice. However, this belief is not without its own opponents. To many scholars, teaching languages cannot be devoid of teaching cultural values of the target language, which tacitly aims at denigrating cultural values of the community of the learners who are learning it. The ultimate purpose of such cultural oppression, according to the...

Drawing on research areas such as estimation, innumeracy, attitude, scientific conceptual change, social cognition, and judgment and decision making, we offer results from a paradigm we call Numerically-Driven Inferencing (Ranney, Cheng, Nelson, & Garcia de Osuna, 2001). NDI includes observing the effects of presenting critical, germane, and credible base rates that are relevant to social polic...

We have developed a new series of multi-agent reinforcement learning algorithms that choose a policy based on beliefs about co-players policies. The algorithms are applicable to situations where a state is fully observable by the agents, but there is no limit on the number of players. Some of the algorithms employ embedded beliefs to handle the cases that co-players are also choosing a policy b...