Solving infinite-horizon Dec-POMDPs using Finite State Controllers within JESP.
Yang YouVincent ThomasFrancis ColasOlivier BuffetPublished in: ICTAI (2021)
Keyphrases
- infinite horizon
- dec pomdps
- markov decision problems
- dynamic programming
- long run
- finite horizon
- optimal policy
- optimal control
- decision making under uncertainty
- markov decision processes
- markov decision process
- decision theoretic
- partially observable
- average cost
- single agent
- theoretical justification
- continuous state
- multi agent
- policy iteration
- state space
- finite state
- multi agent systems
- control system
- lead time
- formal models
- linear programming
- optimal plans