From Reinforcement Learning Towards Artificial General Intelligence.
Filipe Marinho RochaVítor Santos CostaLuís Paulo ReisPublished in: WorldCIST (2) (2020)
Keyphrases
- artificial general intelligence
- reinforcement learning
- human level
- general intelligence
- function approximation
- reinforcement learning algorithms
- temporal difference
- state space
- model free
- optimal control
- learning algorithm
- optimal policy
- multi agent
- machine learning
- multi agent reinforcement learning
- robotic control
- dynamic programming
- partially observable
- markov decision processes
- action selection
- learning process
- temporal difference learning
- stochastic approximation
- image processing
- cognitive architectures