On Normative Reinforcement Learning via Safe Reinforcement Learning.
Emery A. NeufeldEzio BartocciAgata CiabattoniPublished in: PRIMA (2022)
Keyphrases
- reinforcement learning
- function approximation
- reinforcement learning algorithms
- state space
- optimal policy
- learning algorithm
- markov decision processes
- robotic control
- model free
- multi agent
- temporal difference
- dynamic programming
- policy search
- perceptual aliasing
- machine learning
- temporal difference learning
- learning agents
- partially observable
- markov decision process
- control problems
- learning capabilities
- case study
- neural network
- direct policy search