The Value Function Polytope in Reinforcement Learning.
Robert DadashiAdrien Ali TaïgaNicolas Le RouxDale SchuurmansMarc G. BellemarePublished in: CoRR (2019)
Keyphrases
- reinforcement learning
- case study
- control policy
- function approximators
- genetic algorithm
- learning algorithm
- lattice points
- temporal difference
- radial basis function
- robotic control
- temporal difference learning
- semidefinite
- reinforcement learning algorithms
- function approximation
- data sets
- random walk
- state space
- mobile robot
- machine learning