Planning in Hierarchical Reinforcement Learning: Guarantees for Using Local Policies

Keyphrases

• Local Policy 100%
• Hierarchical Reinforcement Learning 100%
• Traveling Salesman Problem 50%
• Computational Resources 50%
• Easy-to-implement 50%
• Local Solution 50%
• Discounted Reward 50%
• Stochastic Policy 50%

Computer Science

• Reinforcement Learning 100%
• Traveling Salesman Problem 50%
• Stochastic Policy 50%
• Experimental Result 50%
• Computational Resource 50%