Exploiting Separability in Multiagent Planning with Continuous-State MDPs (Extended Abstract).
Jilles Steeve DibangoyeChristopher AmatoOlivier BuffetFrançois CharpilletPublished in: IJCAI (2015)
Keyphrases
- continuous state
- extended abstract
- dec pomdps
- multiagent planning
- reinforcement learning
- finite state
- robot navigation
- planning problems
- action space
- state dependent
- control policies
- partially observable markov decision processes
- continuous state and action spaces
- state space
- markov decision processes
- state action
- optimal policy
- markov chain
- machine learning