Conflicts about teamwork in partially observable domains: Hybrids to the rescue

Pradeep Varakantham


Agents or agent teams deployed to assist humans often face the challenges of monitoring the state of key processes in their environment (including the state of their human users themselves) and making periodic decisions based on such monitoring. POMDPs appear well suited to enable agents to address these challenges, given the uncertain environment and cost of actions, but optimal policy generation for POMDPs is computationally expensive. This work uses the BDI-POMDP hybrid at the macro level, and exploits dynamics of the domain to speedup policy computation in POMDPs. In many real-world multiagent applications such as distributed sensor nets, a network of agents is formed based on each agent's limited interactions with a small number of neighbors. While distributed POMDPs capture the real-world uncertainty in multiagent domains, they fail to exploit such locality of interaction. Distributed constraint optimization (DCOP) captures the locality of interaction but fails to capture planning under uncertainty. This work presents a new model synthesized from distributed POMDPs and DCOPs, called Networked Distributed POMDPs (ND-POMDPs).

Maintained by Changki Min