Multiagent value iteration algorithms in dynamic programming and reinforcement learning

Mathematics

• Reinforcement Learning 100%
• Value Iteration 94%
• Dynamic Programming 66%
• Policy 27%
• Policy Iteration 27%
• Shortest Path Problem 11%
• Optimal Policy 10%
• Contraction Mapping 10%
• Infinite Horizon 10%
• Linearly 7%
• Knowledge 7%
• Distinct 6%
• Standards 5%
• Operator 4%

Engineering & Materials Science

• Reinforcement learning 66%
• Dynamic programming 64%