Distributional Reinforcement Learning with Maximum Mean Discrepancy.
Thanh Tang NguyenSunil GuptaSvetha VenkateshPublished in: CoRR (2020)
Keyphrases
- reinforcement learning
- function approximation
- reinforcement learning algorithms
- model free
- multi agent
- state space
- co occurrence
- learning algorithm
- feature selection
- control problems
- genetic algorithm
- policy search
- temporal difference
- maximum number
- optimal control
- website
- learning problems
- transfer learning
- optimal policy
- markov chain
- dynamic programming
- robot control
- temporal difference learning
- continuous state
- autonomous learning
- machine learning