Feedback-based tree search for reinforcement learning

Engineering

• Evaluator 100%
• Leaf Node 100%
• Artificial Intelligence 100%
• Reinforcement Learning 100%
• Value Function 50%
• Markov Decision Process 50%
• Application Domain 50%
• Estimated Value 50%
• Finite Horizon 50%
• Deep Neural Network 50%
• Reinforcement Learning Technique 50%
• Terminal Condition 50%

Computer Science

• Tree Search 100%
• Reinforcement Learning 100%
• Artificial Intelligence 16%
• Search Procedure 16%
• Deep Neural Network 16%
• Artificial Intelligence Applications 16%
• Decision Trees 16%
• Learning Technique 16%
• Application Domain 16%
• Markov Decision Process 16%
• Function Value 16%

Keyphrases

• Monte Carlo Tree Search 100%
• Tree Search 100%
• Artificial Intelligence Agents 25%
• Finite Horizon Problem 25%