Safe Policy Synthesis in Multi-Agent POMDPs via Discrete-Time Barrier Functions.
Mohamadreza AhmadiAndrew SingletaryJoel W. BurdickAaron D. AmesPublished in: CDC (2019)
Keyphrases
- multi agent
- partially observable markov decision processes
- finite state
- reinforcement learning
- optimal policy
- partially observable
- policy search
- markov chain
- markov decision processes
- belief state
- single agent
- state space
- dynamic programming
- continuous state
- markov decision problems
- policy iteration algorithm
- functional programs
- decision problems
- cooperative
- markov decision process
- distributed constraint optimization
- optimal solution
- policy gradient
- planning under uncertainty
- multi agent systems
- multiagent systems
- belief space
- decision processes
- machine learning
- dec pomdps
- model checking
- partially observable stochastic games