Improving Generalization of Reinforcement Learning with Minimax Distributional Soft Actor-Critic.
Yangang RenJingliang DuanYang GuanShengbo Eben LiPublished in: CoRR (2020)
Keyphrases
- actor critic
- reinforcement learning
- temporal difference
- policy gradient
- reinforcement learning algorithms
- approximate dynamic programming
- optimal control
- function approximation
- neuro fuzzy
- gradient method
- policy iteration
- evaluation function
- model free
- state space
- markov decision processes
- control problems
- rl algorithms
- policy gradient methods
- optimal policy
- temporal difference learning
- dynamic programming
- multi agent
- natural actor critic
- machine learning
- action selection
- optimization methods
- learning problems
- function approximators
- decision problems
- learning algorithm