Standard value function approaches to finding policies for Partially Observable Markov Decision Processes (POMDPs) are generally considered to be intractable for large models. The intractability of these algorithms is to a large extent a consequence of computing an exact, optimal policy over the entire belief space. However, in real-world POMDP problems, computing the optimal policy for the ful...

While POMDPs (partially observable markov decision problems) are a popular computational model with wide-ranging applications, the computational cost for optimal policy generation is prohibitive. Researchers are investigating ever-more efficient algorithms, yet many applications demand such algorithms bound any loss in policy quality when chasing efficiency. To address this challenge, we presen...

How does explaining novel observations influence the extent to which learners revise beliefs in the face of anomalies – observations inconsistent with their beliefs? On one hand, explaining could recruit prior beliefs and reduce belief revision if learners “explain away” or discount anomalies. On the other hand, explaining could promote belief revision by encouraging learners to modify beliefs ...

There has been substantial progress in the field of Reinforcement Learning (RL) in recent years. Many RL applications have achieved remarkable success by taking advantage of as much prior knowledge (PK) as possible. However, they often do so through problem-specific heuristics, due to the lack of a general framework capable of incorporating broad PK. We take the first steps towards a global RL ...

Agents or agent teams deployed to assist humans often face the challenge ofmonitoring state of key processes in their environment, including the state of their human users, and making periodic decisions based on such monitoring. The challenge is particularly difficult given the significant observational uncertainty, and uncertainty in the outcome of agent’s actions. POMDPs (partially observable...