Discounted Reinforcement Learning is Not an Optimization Problem.
Abhishek NaikRoshan ShariffNiko YasuiRichard S. SuttonPublished in: CoRR (2019)
Keyphrases
- reinforcement learning
- optimal policy
- dynamic programming
- markov decision processes
- global optimization
- optimization process
- state space
- optimization algorithm
- constrained optimization
- reinforcement learning algorithms
- markov decision process
- optimization method
- search space
- transfer learning
- genetic algorithm
- optimization methods
- robotic control