Normality-Guided Distributional Reinforcement Learning for Continuous Control.
Ju-Seung ByunAndrew PerraultPublished in: CoRR (2022)
Keyphrases
- reinforcement learning
- optimal control
- control problems
- control system
- control policy
- control method
- co occurrence
- multi agent
- state space
- function approximation
- control strategies
- robot control
- action space
- data sets
- fitted q iteration
- adaptive control
- reinforcement learning methods
- control strategy
- real valued
- e learning
- continuous variables
- model free
- markov decision processes
- action selection
- transfer learning
- optimal policy
- dynamic programming
- feedback control
- learning process
- multi agent reinforcement learning
- robotic control
- learning algorithm