Scalable Anytime Planning for Multi-Agent MDPs (Extended Abstract).
Shushman ChoudhuryJayesh K. GuptaMykel J. KochenderferPublished in: IJCAI (2022)
Keyphrases
- extended abstract
- multi agent
- planning under uncertainty
- reinforcement learning
- stochastic domains
- markov decision processes
- decision theoretic planning
- dec pomdps
- sequential decision making problems
- single agent
- planning problems
- partially observable markov decision processes
- probabilistic planning
- ai planning
- multi agent planning
- markov decision problems
- partially observable
- cooperative
- multi agent systems
- blocks world
- autonomous agents
- state space
- optimal policy
- heuristic search
- initial state
- intelligent agents
- reinforcement learning problems
- dynamical systems
- classical planning
- multiple agents
- decision theoretic
- dynamic programming
- multiagent systems