Interac-DEC-MDP: Towards the Use of Interactions in DEC-MDP.
Vincent ThomasChristine BourjotVincent ChevrierPublished in: AAMAS (2004)
Keyphrases
- markov decision processes
- markov decision process
- optimal policy
- utility function
- state space
- reinforcement learning
- finite state
- linear program
- initial state
- action sets
- dynamic programming algorithms
- planning under uncertainty
- linear programming
- dynamic programming
- reward function
- action space
- markov decision problems
- databases
- decision problems
- average cost
- average reward
- machine learning
- factored mdps
- state and action spaces
- database