Stochastically Dominant Distributional Reinforcement Learning.
John D. MartinMichal LyskawinskiXiaohu LiBrendan J. EnglotPublished in: CoRR (2019)
Keyphrases
- reinforcement learning
- function approximation
- markov decision processes
- control problems
- state space
- co occurrence
- learning algorithm
- continuous state
- reinforcement learning algorithms
- action selection
- optimal policy
- multiscale
- learning capabilities
- function approximators
- learning agents
- multi agent reinforcement learning
- robotic control
- direct policy search
- evolutionary algorithm
- multi agent
- optimal control
- model free
- case study
- social networks
- machine learning