A sparse sampling algorithm for near-optimal planning in large Markov decision processes

Keyphrases

• Sampling Algorithm 100%
• Near-optimal 100%
• Markov Decision Process 100%
• Optimal Planning 100%
• Sparse Sampling 100%
• Stochastic Environment 16%
• Optimal Policy 16%
• Partially Observable Markov Decision Process 16%
• Discount Factor 16%
• Good Strategies 16%
• Real-world Problems 16%
• Optimal Actions 16%
• Infinite State Space 16%
• Number of States 16%
• Near-optimal Policy 16%
• Generative Models 16%
• Reinforcement Learning Algorithm 16%
• Degree of Approximation 16%
• Planning Scale 16%
• State Space Size 16%
• Traditional Planning 16%
• Mentation 16%

Computer Science

• Sampling Algorithm 100%
• Markov Decision Process 100%
• State Space 28%
• Approximation (Algorithm) 14%
• Reinforcement Learning 14%
• Optimal Action 14%
• Generative Model 14%
• Traditional Planning 14%

Mathematics

• Markov Decision Process 100%
• Running Time 50%
• Optimal Policy 33%
• Stochastics 16%
• Discount Factor 16%
• Partially Observable Markov Decision Process 16%
• Degree of Approximation 16%