Procedural Memory Augmented Deep Reinforcement Learning.
Ying MaJoseph BrooksHongming LiJosé C. PríncipePublished in: IEEE Trans. Artif. Intell. (2020)
Keyphrases
- reinforcement learning
- memory requirements
- memory usage
- function approximation
- reinforcement learning algorithms
- object oriented
- computational power
- computing power
- state space
- optimal policy
- low memory
- memory size
- model free
- conceptual knowledge
- temporal difference learning
- stochastic approximation
- action selection
- markov decision processes
- multi agent systems
- multi agent
- policy search
- machine learning
- robotic control
- limited memory
- random access
- optimal control
- main memory
- dynamic programming
- genetic algorithm