IPOMDP-Net: A Deep Neural Network for Partially Observable Multi-Agent Planning Using Interactive POMDPs.
Yanlin HanPiotr J. GmytrasiewiczPublished in: AAAI (2019)
Keyphrases
- partial observability
- partially observable
- multi agent planning
- belief state
- markov decision processes
- state space
- reinforcement learning
- decision problems
- dynamical systems
- partially observable markov decision processes
- belief space
- partial observations
- agent programming
- markov decision problems
- infinite horizon
- orders of magnitude
- partially observable markov decision process
- reward function
- optimal solution
- optimal control
- planning problems
- search space
- multi agent systems