On the Combinatorial Multi-Armed Bandit Problem with Markovian Rewards.
Yi GaiBhaskar KrishnamachariMingyan LiuPublished in: GLOBECOM (2011)
Keyphrases
- total reward
- reinforcement learning
- markov decision processes
- multiarmed bandit
- bandit problems
- long term and short term
- action selection
- multi armed bandit
- multi armed bandits
- information systems
- lower bound
- computational complexity
- machine learning
- computational geometry
- multi agent systems
- bayesian networks
- image segmentation
- multi armed bandit problems