Multiagent Rollout and Policy Iteration for POMDP with Application to Multi-Robot Repair Problems

Mathematics

• Multi-robot 100%
• Partially Observable Markov Decision Process 84%
• Policy Iteration 74%
• Repair 57%
• Policy 16%
• Robot 13%
• Standards 12%
• State Space 9%
• Look-ahead 7%
• Partial Information 6%
• Function Approximation 6%
• Iteration Scheme 6%
• Building Blocks 6%
• Infinite Horizon 6%
• Classifier 6%
• Computational Experiments 6%
• Optimise 5%
• Iteration Method 5%
• Dynamic Programming 5%
• Cost Function 5%
• Neural Networks 5%
• Verify 4%
• Requirements 4%
• Cardinality 4%
• Strictly 4%
• Costs 4%
• Simulation Study 4%
• Partial 3%
• Line 3%
• Observation 3%
• Demonstrate 3%
• Performance 3%
• Graph in graph theory 2%
• Class 1%

Engineering & Materials Science

• Repair 41%
• Robots 32%
• Graph structures 12%
• Dynamic programming 9%
• Cost functions 9%
• Classifiers 7%
• Neural networks 6%
• Costs 3%
• Experiments 3%