The Architectural Implications of Distributed Reinforcement Learning on CPU-GPU Systems.
Ahmet Fatih InciEvgeny BolotinYaosheng FuGal DalalShie MannorDavid W. NellansDiana MarculescuPublished in: CoRR (2020)
Keyphrases
- reinforcement learning
- distributed systems
- distributed computation
- expert systems
- management system
- complex systems
- graphics processing units
- real time
- multi agent
- mission critical
- retrieval systems
- data intensive
- autonomous mobile
- commercial off the shelf
- open systems
- data transfer
- fault tolerant
- markov decision processes
- mobile agents
- computer systems
- data management
- general purpose
- neural network