Scalable Planning in Multi-Agent MDPs.
Dinuka SahabanduLuyao NiuAndrew ClarkRadha PoovendranPublished in: CoRR (2021)
Keyphrases
- multi agent
- planning under uncertainty
- reinforcement learning
- markov decision processes
- stochastic domains
- planning problems
- probabilistic planning
- partially observable
- partially observable markov decision processes
- dec pomdps
- state space
- ai planning
- single agent
- multi agent planning
- markov decision problems
- cooperative
- decision theoretic planning
- initial state
- decision theoretic
- sequential decision making problems
- multi agent systems
- optimal policy
- reactive agents
- planning domains
- heuristic search
- markov decision process
- heterogeneous agents
- dynamic programming
- factored markov decision processes
- planning systems
- finite horizon
- agent behavior
- linear programming
- dynamical systems
- reinforcement learning problems
- machine learning
- path finding