Optimally Solving Dec-POMDPs as Continuous-State MDPs.
Jilles Steeve DibangoyeChristopher AmatoOlivier BuffetFrançois CharpilletPublished in: J. Artif. Intell. Res. (2016)
Keyphrases
- dec pomdps
- continuous state
- sequential decision making problems
- reinforcement learning
- finite state
- robot navigation
- state dependent
- control policies
- partially observable markov decision processes
- action space
- planning problems
- dynamic programming
- state space
- multi agent
- markov decision problems
- state action
- real valued
- markov decision processes
- optimal policy
- infinite horizon
- function approximation
- decision problems
- hidden state
- control system
- markov chain
- machine learning