Policy gradient reinforcement learning with environmental dynamics and action-values in policies

Mathematics

• Reinforcement Learning 100%
• Policy 65%
• Rule Learning 60%
• Knowledge 50%
• Gradient 50%
• Pursuit 33%
• Learning 24%
• Objective function 22%
• Simulation 16%
• State Transition 16%
• Value Function 12%
• Framework 7%

Engineering & Materials Science

• Reinforcement learning 66%
• Set theory 10%