Two-Memory Reinforcement Learning.
Zhao YangThomas M. MoerlandMike PreussAske PlaatPublished in: CoRR (2023)
Keyphrases
- reinforcement learning
- function approximation
- reinforcement learning algorithms
- memory requirements
- machine learning
- memory size
- memory usage
- optimal policy
- low memory
- markov decision processes
- artificial neural networks
- multi agent
- action selection
- learning algorithm
- random access
- database systems
- robotic control
- real time
- stochastic approximation
- limited memory
- past experience
- dynamic programming
- model free
- computational power
- learning process
- state space