SEM: Safe exploration mask for q-learning.
Chengbin XuanFeng ZhangHak-Keung LamPublished in: Eng. Appl. Artif. Intell. (2022)
Keyphrases
- action selection
- exploration strategy
- reinforcement learning
- state space
- cooperative
- function approximation
- multi agent
- unknown environments
- learning algorithm
- data mining
- markov decision processes
- optimal policy
- learning rate
- reinforcement learning algorithms
- policy iteration
- machine learning
- dynamic programming
- model free
- data analysis
- stochastic approximation
- interactive exploration
- real time
- active exploration
- bucket brigade