A note on reinforcement learning with Wasserstein distance regularisation, with applications to multipolicy learning.
Mohammed Amin AbdullahAldo PacchianoMoez DraiefPublished in: CoRR (2018)
Keyphrases
- reinforcement learning
- learning process
- learning algorithm
- learning problems
- learning mechanism
- learning systems
- learning capabilities
- learning tasks
- online learning
- unsupervised learning
- euclidean distance
- state space
- prior knowledge
- learning environment
- multi agent
- stochastic games
- learning agents
- temporal difference learning
- multi agent reinforcement learning