
Solving TransitionIndependent Multiagent MDPs with Sparse Interactions (Extended version)
In cooperative multiagent sequential decision making under uncertainty,...
read it

ResourceDriven MissionPhasing Techniques for Constrained Agents in Stochastic Environments
Because an agents resources dictate what actions it can possibly take, i...
read it

Learning to Collaborate in Markov Decision Processes
We consider a twoagent MDP framework where agents repeatedly solve a ta...
read it

Mixed integer formulations using natural variables for single machine scheduling around a common due date
While almost all existing works which optimally solve justintime sched...
read it

Reinforcement Learning for Heterogeneous Teams with PALO Bounds
We introduce reinforcement learning for heterogeneous teams in which rew...
read it

Qualitative Possibilistic MixedObservable MDPs
Possibilistic and qualitative POMDPs (piPOMDPs) are counterparts of POM...
read it

On Convergence and Optimality of BestResponse Learning with Policy Types in Multiagent Systems
While many multiagent algorithms are designed for homogeneous systems (i...
read it
Compact Mathematical Programs For DECMDPs With Structured Agent Interactions
To deal with the prohibitive complexity of calculating policies in Decentralized MDPs, researchers have proposed models that exploit structured agent interactions. Settings where most agent actions are independent except for few actions that affect the transitions and/or rewards of other agents can be modeled using EventDriven Interactions with Complex Rewards (EDICR). Finding the optimal joint policy can be formulated as an optimization problem. However, existing formulations are too verbose and/or lack optimality guarantees. We propose a compact Mixed Integer Linear Program formulation of EDICR instances. The key insight is that most action sequences of a group of agents have the same effect on a given agent. This allows us to treat these sequences similarly and use fewer variables. Experiments show that our formulation is more compact and leads to faster solution times and better solutions than existing formulations.
READ FULL TEXT
Comments
There are no comments yet.