Hierarchical Reinforcement Learning: Approximating Optimal Discounted TSP Using Local Policies.
Tom ZahavyAvinatan HassidimHaim KaplanYishay MansourPublished in: CoRR (2018)
Keyphrases
- hierarchical reinforcement learning
- discounted reward
- average reward
- optimal policy
- markov decision processes
- dynamic programming
- reinforcement learning
- optimal solution
- markov decision process
- total reward
- long run
- state abstraction
- reward function
- traveling salesman problem
- infinite horizon
- model free
- average cost
- metaheuristic
- sufficient conditions
- finite horizon
- decision problems
- finite state
- stationary policies
- markov chain
- ant colony optimization
- linear programming