Distributional Reinforcement Learning via Sinkhorn Iterations.
Ke SunYingnan ZhaoYi LiuBei JiangLinglong KongPublished in: CoRR (2022)
Keyphrases
- reinforcement learning
- co occurrence
- function approximation
- state space
- reinforcement learning algorithms
- markov decision processes
- model free
- databases
- temporal difference learning
- optimal control
- iterative process
- dynamic environments
- transfer learning
- supervised learning
- evaluation function
- multi agent
- decision making
- learning algorithm
- action selection
- temporal difference
- data mining
- partially observable
- data sets
- reinforcement learning methods
- robotic control