SafeTAC: Safe Tsallis Actor-Critic Reinforcement Learning for Safer Exploration.
Dohyeong KimJaeseok HeoSonghwai OhPublished in: IROS (2022)
Keyphrases
- actor critic
- reinforcement learning
- temporal difference
- policy gradient
- approximate dynamic programming
- reinforcement learning algorithms
- optimal control
- action selection
- gradient method
- neuro fuzzy
- function approximation
- policy iteration
- markov decision processes
- rl algorithms
- state space
- supervised learning
- control problems
- reinforcement learning methods
- policy gradient methods
- model free
- monte carlo
- optimal policy
- dynamic programming
- learning algorithm
- machine learning
- negative matrix factorization
- evaluation function
- linear program
- transfer learning
- multi agent
- neural network