Empirical evaluation of MDP-based DASH player.
Ayub BokaniSayed Amir HoseiniMahbub HassanSalil S. KanherePublished in: ITNAC (2015)
Keyphrases
- empirical evaluation
- markov decision processes
- markov decision process
- utility function
- state space
- optimal policy
- game play
- soccer games
- markov decision problems
- finite state
- theorem proving
- linear programming
- reinforcement learning
- repeated games
- planning under uncertainty
- linear program
- initial state
- neural network
- multi agent
- infinite horizon
- policy iteration
- action space
- average reward
- machine learning