Revisiting Recurrent Reinforcement Learning with Memory Monoids.
Steven D. MoradChris LuRyan KortvelesyStephan LiwickiJakob N. FoersterAmanda ProrokPublished in: CoRR (2024)
Keyphrases
- reinforcement learning
- function approximation
- memory requirements
- reinforcement learning algorithms
- multi agent
- state space
- feed forward
- temporal difference learning
- memory space
- low memory
- limited memory
- memory usage
- temporal difference
- optimal control
- recurrent neural networks
- optimal policy
- information systems
- learning algorithm
- learning problems
- markov decision processes
- action selection
- information processing
- supervised learning
- learning process
- partially observable
- neural network
- multi agent reinforcement learning
- real time