Solving multiagent assignment Markov decision processes.
Scott ProperPrasad TadepalliPublished in: AAMAS (1) (2009)
Keyphrases
- markov decision processes
- transition matrices
- planning under uncertainty
- semi markov decision processes
- multi agent
- stochastic games
- optimal policy
- state space
- finite state
- reinforcement learning
- markov decision problems
- decision theoretic planning
- average reward
- stochastic shortest path
- dynamic programming
- policy iteration
- average cost
- cooperative
- partially observable
- reachability analysis
- reinforcement learning algorithms
- finite horizon
- infinite horizon
- risk sensitive
- markov decision process
- decision theoretic
- dec pomdps
- model based reinforcement learning
- objective function
- action space
- multiagent systems
- markov chain
- state abstraction
- search algorithm
- state and action spaces
- machine learning