Task-Agnostic Safety for Reinforcement Learning.
Md Asifur RahmanSarra AlqahtaniPublished in: AISec@CCS (2023)
Keyphrases
- reinforcement learning
- state space
- function approximation
- optimal policy
- model free
- direct policy search
- learning algorithm
- markov decision processes
- neural network
- control problems
- least squares
- dynamic programming
- multi agent
- wireless sensor networks
- transfer learning
- information retrieval
- machine learning
- action selection
- temporal difference
- partially observable
- real world
- action space
- learning agents
- temporal difference learning
- reinforcement learning methods
- safety critical
- data sets