Safe Reinforcement Learning via a Model-Free Safety Certifier.
Amir ModaresNasser SadatiBabak EsmaeiliFarnaz Adib YaghmaieHamidreza ModaresPublished in: IEEE Trans. Neural Networks Learn. Syst. (2024)
Keyphrases
- model free
- reinforcement learning
- reinforcement learning algorithms
- function approximation
- temporal difference
- policy evaluation
- rl algorithms
- markov decision processes
- policy iteration
- state space
- average reward
- learning algorithm
- least squares
- supervised learning
- learning styles
- learning process
- multi agent
- temporal difference learning
- reinforcement learning methods
- genetic algorithm
- dynamic programming
- action selection