Constrained-Action POMDPs for Multi-Agent Intelligent Knowledge Distribution.
Michael C. FowlerPratap TokekarT. Charles ClancyRyan K. WilliamsPublished in: ICRA (2018)
Keyphrases
- multi agent
- reinforcement learning
- partially observable markov decision processes
- multi agent systems
- cooperative
- agent oriented
- single agent
- partially observable stochastic games
- machine learning
- action selection
- finite state
- markov decision processes
- multiagent systems
- spatial distribution
- intelligent agents
- state space
- initial state
- action sequences
- state action
- distributed constraint optimization
- continuous action
- extensive form games
- objective function