Distributional policy optimization: An alternative approach for continuous control

Keyphrases

• Continuous Control 100%
• Policy Optimization 100%
• Actor-critic 100%
• Probability Distribution 66%
• Policy Gradient Method 66%
• Local Motion 33%
• Action Space 33%
• Suboptimal Solutions 33%
• Distribution Function 33%
• Arbitrary Distribution 33%
• Distribution Class 33%
• Gradient Method 33%
• Policy Representation 33%
• Policy Actors 33%
• Continuous Action Space 33%
• Continuous Domain 33%
• Policy Gradient 33%
• Parametric Distribution 33%

Computer Science

• Gradient Method 100%
• Continuous Control 100%
• Optimization Policy 100%
• Fundamental Problem 50%
• Continuous Domain 50%
• Class Distribution 50%