From minimax value to low-regret algorithms for online Markov decision processes

Keyphrases

• Markov Decision Process 100%
• Regret 100%
• Minimax Values 100%
• Process Settings 50%
• Computationally Efficient 25%
• Learning Process 25%
• Cost Function 25%
• Unpredictable Environment 25%
• Varying Environment 25%
• Process Framework 25%
• Non-stationary Environments 25%
• Online Learning Algorithm 25%
• Deriving Algorithms 25%

Computer Science

• Markov Decision Process 100%
• And-States 25%
• Learning Process 25%
• Learning Algorithm 25%
• Online Learning 25%
• Process Framework 25%