Reinforcement Learning with Fast and Forgetful Memory.
Steven D. MoradRyan KortvelesyStephan LiwickiAmanda ProrokPublished in: CoRR (2023)
Keyphrases
- reinforcement learning
- memory usage
- function approximation
- optimal policy
- markov decision processes
- learning algorithm
- multi agent
- state space
- memory requirements
- machine learning
- memory space
- low memory
- memory size
- temporal difference
- model free
- main memory
- transfer learning
- learning problems
- associative memory
- computational power
- least squares
- hidden markov models
- learning process
- e learning
- learning agents
- real world
- data sets