A Convergent Recursive Least Squares Approximate Policy Iteration Algorithm for Multi-Dimensional Markov Decision Process with Continuous State and Action Spaces

Keyphrases

• Continuous State Space 100%
• Recursive Least Squares 100%
• Approximate Policy Iteration 100%
• Policy Gradient Method 100%
• Continuous Action Space 100%
• Value Policy 33%
• Function Space 33%
• Policy Values 33%
• Approximate Policy 33%
• Policy Space 33%
• Successive Approximation 33%
• Optimal Value Function 33%
• Mean Absolute Deviation 33%

Mathematics

• Least Square 100%
• Action Space 100%
• Markov Decision Process 100%
• Successive Approximation 25%