S-MDP: Streaming With Markov Decision Processes.
Koffka KhanWayne GoodridgePublished in: IEEE Trans. Multim. (2019)
Keyphrases
- markov decision processes
- optimal policy
- transition matrices
- finite state
- data streams
- state space
- markov decision process
- reinforcement learning
- dynamic programming
- policy iteration
- average cost
- infinite horizon
- decision theoretic planning
- planning under uncertainty
- reinforcement learning algorithms
- partially observable
- factored mdps
- state and action spaces
- finite horizon
- action space
- reward function
- action sets
- decision processes
- average reward
- risk sensitive
- discount factor
- model based reinforcement learning
- real time dynamic programming
- semi markov decision processes
- multi agent