Cooperative off-policy prediction of Markov decision processes in adaptive networks.
Sergio Valcarcel MacuaJianshu ChenSantiago ZazoAli H. SayedPublished in: ICASSP (2013)
Keyphrases
- markov decision processes
- cooperative
- state space
- optimal policy
- finite state
- reinforcement learning
- transition matrices
- dynamic programming
- policy iteration
- average reward
- reinforcement learning algorithms
- planning under uncertainty
- decision theoretic planning
- action space
- reachability analysis
- markov decision process
- factored mdps
- state and action spaces
- partially observable
- stochastic games
- finite horizon
- risk sensitive
- decision processes
- infinite horizon
- semi markov decision processes
- model based reinforcement learning
- average cost
- reward function
- game theory
- decision problems
- model checking
- sufficient conditions
- multi agent systems
- multi agent